© 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. 34-GEMMASCOPE-RES-131K
    7. 30401
    Prev
    Next
    INDEX
    Explanations

    perf or perfor prefix

    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_34/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
    Fau
    -0.82
    ופה
    -0.77
    nume
    -0.77
    りましたが
    -0.75
    falcon
    -0.75
    LETS
    -0.75
    occupe
    -0.74
    奋斗
    -0.73
    ồm
    -0.71
     external
    -0.71
    POSITIVE LOGITS
     Perf
    1.45
     perf
    1.31
    Perf
    1.16
     pref
    1.10
    perf
    1.10
     Pref
    1.08
     Perfection
    1.05
     perfusion
    1.00
    Pref
    0.97
    PERF
    0.97
    Activations Density 0.022%

    No Known Activations