© 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. 78418
    Prev
    Next
    INDEX
    Explanations

    default values or actions

    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
    Характеристики
    -0.75
    ább
    -0.72
    dion
    -0.72
    ULER
    -0.70
     ambul
    -0.70
     Bort
    -0.69
     quoque
    -0.69
    찡
    -0.68
    vosť
    -0.67
     Dionys
    -0.66
    POSITIVE LOGITS
     default
    7.91
    default
    6.91
     defaults
    6.06
     Default
    6.00
    Default
    5.97
    默认
    5.84
    DEFAULT
    5.44
     DEFAULT
    5.34
    defaults
    5.06
     defaulted
    4.94
    Activations Density 0.316%

    No Known Activations