© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49034
    Prev
    Next
    INDEX
    Explanations

    good quality or skill

    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
    ПА
    -0.93
    ícias
    -0.91
    vateľ
    -0.87
    backers
    -0.85
    殄
    -0.85
     Poz
    -0.84
    EDU
    -0.83
    Classic
    -0.81
     <",
    -0.81
    FET
    -0.81
    POSITIVE LOGITS
     good
    3.89
     excellent
    2.81
    good
    2.64
     skilled
    2.34
     better
    2.16
     proficient
    2.14
     хоро
    2.05
     great
    2.03
     adept
    1.98
     excel
    1.92
    Activations Density 0.054%

    No Known Activations