© 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. 10-GEMMASCOPE-RES-131K
    7. 13961
    Prev
    Next
    INDEX
    Explanations

    hour or hours

    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
     ”
    -2.14
     metaphorical
    -2.05
     ''
    -2.02
     incite
    -1.99
    zoeken
    -1.94
     متحده
    -1.92
     annoy
    -1.91
     –
    -1.88
    jenige
    -1.87
    ashing
    -1.87
    POSITIVE LOGITS
    趼
    2.39
    </strong>
    2.38
    釭
    2.31
    慫
    2.22
    ).
    2.13
    ༵
    2.08
     untuk
    2.08
     zusätz
    2.06
    .
    2.06
    
    2.05
    Activations Density 0.005%

    No Known Activations