© 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. 73326
    Prev
    Next
    INDEX
    Explanations

    related topics and types

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

    The neuron responds strongly to common web‐UI and navigation cue phrases and headings—things like “you can,” “search for,” “Types,” “Applications,” “Research,” “KINDLE,” “AUDIO BOOKS,” etc.

    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
    gunakan
    -1.47
    pasti
    -1.13
    unakan
    -1.10
    undur
    -1.05
     my
    -1.05
    生病
    -1.05
     フィギュア
    -1.03
    他们
    -1.03
    adple
    -1.03
     then
    -1.02
    POSITIVE LOGITS
    ocusing
    1.14
     asesinado
    1.12
     schuhe
    1.10
     inspirasi
    1.09
    aggiare
    1.09
     kemungkinan
    1.05
    豪華
    1.04
    ricated
    1.03
     sosok
    1.03
    plings
    1.03
    Activations Density 0.001%

    No Known Activations