© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28519
    Prev
    Next
    INDEX
    Explanations

    Keith Olbermann

    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
     alcun
    -1.13
     クッキー
    -1.08
     显
    -1.02
     Betten
    -0.98
     to
    -0.97
     it
    -0.93
     if
    -0.92
    也沒
    -0.90
     ウール
    -0.90
     lopez
    -0.89
    POSITIVE LOGITS
     tránsito
    0.96
     מִ
    0.90
     cuero
    0.89
     bienestar
    0.88
     cité
    0.86
    public
    0.86
    都
    0.85
    jogador
    0.85
    tanda
    0.84
    camino
    0.83
    Activations Density 0.001%

    No Known Activations