© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25300
    Prev
    Next
    INDEX
    Explanations

    Philpot, we noticed, power light, DNA double

    np_acts-logits-general · gemini-2.5-flash-lite

    format specifiers in programming language code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by the contents of quoted string literals (i.e. characters inside "" sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     while
    -1.62
     it
    -1.43
     even
    -1.35
     mientras
    -1.25
     our
    -1.23
     enquanto
    -1.21
     might
    -1.21
     mentre
    -1.20
     because
    -1.18
    为例
    -1.15
    POSITIVE LOGITS
     stod
    1.23
    БЕ
    1.20
     asker
    1.16
    tiert
    1.15
     Recep
    1.14
     ladite
    1.14
    órica
    1.13
     tsar
    1.12
     smel
    1.11
     Somme
    1.10
    Activations Density 0.006%

    No Known Activations