© 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. 28054
    Prev
    Next
    INDEX
    Explanations

    characteristics andscreening and

    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
    などを
    -1.20
     HAVING
    -1.13
    okkal
    -1.13
     The
    -1.12
    があり
    -1.08
     vierten
    -1.07
     MINIMUM
    -1.06
     proposent
    -1.05
     schuldig
    -1.05
     dritten
    -1.04
    POSITIVE LOGITS
     banyo
    1.14
     estekak
    1.11
     etek
    1.09
     tijden
    1.09
     Keep
    1.09
    quelize
    1.08
    ítico
    1.07
    ぶりの
    1.07
    ARANCE
    1.07
    uuml
    1.05
    Activations Density 0.002%

    No Known Activations