© 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. 10-GEMMASCOPE-RES-131K
    7. 61179
    Prev
    Next
    INDEX
    Explanations

    `nofirst` `aknowledgeable` `mysound` `nodiscard` `dorections` `fore` `somerule` `myscript`

    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_10/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
     now
    -1.88
    </em>
    -1.78
     only
    -1.77
     since
    -1.75
    </td>
    -1.73
     this
    -1.69
     should
    -1.67
     can
    -1.66
     at
    -1.55
     have
    -1.54
    POSITIVE LOGITS
    ⩴
    1.61
    ulates
    1.61
    isn
    1.60
     dessous
    1.50
    ANAL
    1.49
    those
    1.49
     iti
    1.49
    卺
    1.49
    ests
    1.48
     sier
    1.48
    Activations Density 0.087%

    No Known Activations