© 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. 10-GEMMASCOPE-RES-131K
    7. 43326
    Prev
    Next
    INDEX
    Explanations

    separators and structure

    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
    </table>
    -1.59
     how
    -1.58
     mourut
    -1.48
    心臓
    -1.45
     where
    -1.42
     with
    -1.40
     répondit
    -1.38
     which
    -1.34
    不止
    -1.34
     impulsar
    -1.32
    POSITIVE LOGITS
    鹩
    1.75
    𓆏
    1.65
     bekym
    1.65
     murale
    1.63
     peluche
    1.62
    itize
    1.62
     pistolet
    1.59
    卺
    1.55
     paille
    1.55
    rals
    1.55
    Activations Density 0.372%

    No Known Activations