© 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. 21358
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     エントランス
    -1.15
    itaji
    -1.15
     unſ
    -1.15
     intentando
    -1.13
    apparently
    -1.06
    鼍
    -1.06
     綿
    -1.06
    סף
    -1.06
    struktion
    -1.05
    ന്ന്
    -1.05
    POSITIVE LOGITS
    </b>
    1.17
     a
    1.13
    "
    1.09
     and
    1.03
    ))
    1.01
    ....
    0.98
     "
    0.95
     Because
    0.94
     )
    0.92
     m
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.