© 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. 22-GEMMASCOPE-RES-131K
    7. 16102
    Prev
    Next
    INDEX
    Explanations

    Tag, Q, Inst, I, png

    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_22/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
     Mereka
    -1.09
     that
    -1.07
     fabriqué
    -1.05
    ΠΑ
    -1.01
     Vitamina
    -0.95
     those
    -0.93
     والش
    -0.92
     граду
    -0.90
     аромат
    -0.89
     tonight
    -0.88
    POSITIVE LOGITS
     Elton
    0.89
    ואל
    0.89
    Totale
    0.88
    带宽
    0.88
    Conjunto
    0.87
    置信
    0.86
    Doubles
    0.86
    票房
    0.85
    ídos
    0.85
     hanem
    0.84
    Activations Density 0.000%

    No Known Activations