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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93341
    Prev
    Next
    INDEX
    Explanations

    accepted Date, Fancy Dress, Transcranial

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

    indentation in code or programming language files.

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

    The neuron fires on numeric tokens (digits and numbers), especially version numbers and other numeric identifiers in code.

    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
    Dawg
    -1.34
    Crítica
    -1.06
     clichés
    -1.06
    ⇐
    -1.05
     most
    -1.02
    hound
    -1.02
    dawg
    -1.01
    三郎
    -1.00
     numerous
    -1.00
     on
    -0.99
    POSITIVE LOGITS
    おわりに
    1.28
    の作成
    1.17
     feuilles
    1.14
     estudiante
    1.13
    老師
    1.13
     forcément
    1.13
     colorear
    1.09
     loved
    1.09
     educativas
    1.09
    そも
    1.06
    Activations Density 0.004%

    No Known Activations