© 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. 22-GEMMASCOPE-RES-131K
    7. 27490
    Prev
    Next
    INDEX
    Explanations

    httpidentification

    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
    емов
    -1.06
     reassure
    -1.01
     silueta
    -1.00
    Landes
    -0.96
    粿
    -0.96
     erschien
    -0.94
    AutoScaleMode
    -0.94
    狽
    -0.93
     vrienden
    -0.93
    clés
    -0.92
    POSITIVE LOGITS
     grandiose
    0.91
    럿
    0.88
    oul
    0.88
    na
    0.88
    ams
    0.86
    快的
    0.85
    o
    0.85
    ent
    0.83
    ety
    0.83
    ils
    0.82
    Activations Density 0.000%

    No Known Activations