© 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. 127726
    Prev
    Next
    INDEX
    Explanations

    database or category names

    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
     also
    -1.30
    啖
    -1.27
    しているので
    -1.27
     velha
    -1.23
     kellett
    -1.22
     dieses
    -1.19
     другая
    -1.18
     colher
    -1.17
     heute
    -1.16
     quí
    -1.14
    POSITIVE LOGITS
    >
    1.93
    tiest
    1.58
     --------
    1.40
    鞴
    1.40
    }
    1.40
    kkkk
    1.39
    ,
    1.39
    orice
    1.39
     ――――――――
    1.38
    signment
    1.38
    Activations Density 0.000%

    No Known Activations