© 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. 22-GEMMASCOPE-RES-131K
    7. 65756
    Prev
    Next
    INDEX
    Explanations

    Java code imports and properties

    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
     both
    -1.32
     Kto
    -1.09
     Synag
    -1.08
     København
    -1.02
     newBuilder
    -1.02
     writeTo
    -1.00
     marchio
    -0.97
     others
    -0.97
     recupero
    -0.94
    そうに
    -0.94
    POSITIVE LOGITS
    ごめん
    1.13
    zydent
    1.01
    榉
    0.96
    Delete
    0.92
    Numero
    0.91
    おわりに
    0.90
     corriger
    0.90
    behör
    0.89
    ínsula
    0.88
     constater
    0.88
    Activations Density 0.005%

    No Known Activations