© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27521
    Prev
    Next
    INDEX
    Explanations

    legal, scientific, or company names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     fhew
    -1.23
     our
    -1.22
     everyone
    -1.11
    🧰
    -1.10
     all
    -1.09
    \#:
    -1.09
    (
    -1.07
     fhall
    -1.05
     we
    -1.04
    私たち
    -1.04
    POSITIVE LOGITS
    addressed
    1.16
    memoized
    1.13
     galima
    1.11
    ⑳
    1.09
     męski
    1.08
    月中
    1.05
     hueso
    1.05
    ⋗
    1.04
    ンピオン
    1.04
    衛門
    1.03
    Activations Density 0.005%

    No Known Activations