© 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. 107086
    Prev
    Next
    INDEX
    Explanations

    constructor parameters

    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
    ensuremath
    -1.00
     various
    -0.91
    :
    -0.85
     geschaffen
    -0.85
     verschiedenen
    -0.84
     zahlreichen
    -0.83
     bedeutend
    -0.80
    ান
    -0.80
    Bottle
    -0.79
     zweifel
    -0.79
    POSITIVE LOGITS
    public
    1.04
    ){}
    1.02
    ,)
    1.02
    )
    0.92
    +}
    0.92
    aconda
    0.90
    private
    0.89
     affez
    0.88
    ֶּ
    0.88
     étrang
    0.87
    Activations Density 0.006%

    No Known Activations