© 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. 93661
    Prev
    Next
    INDEX
    Explanations

    up my alley or for you

    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
    isiert
    -0.94
    entown
    -0.84
    ntomas
    -0.84
    meli
    -0.83
    σια
    -0.83
     protéger
    -0.81
    uberge
    -0.81
     résister
    -0.79
     determinados
    -0.79
    ハー
    -0.78
    POSITIVE LOGITS
     right
    1.52
     for
    1.48
     what
    1.40
     something
    1.39
     suited
    1.27
     exactly
    1.23
     appeal
    1.23
     appeals
    1.22
     appealing
    1.16
    符合
    1.16
    Activations Density 0.027%

    No Known Activations