© 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. 38994
    Prev
    Next
    INDEX
    Explanations

    neighboring elements

    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
     Início
    -1.13
    视着
    -1.05
     Acesso
    -1.05
     pimenta
    -1.02
    toHexString
    -1.02
     masih
    -1.02
    nitive
    -1.02
    觧
    -1.01
     ممکن
    -1.00
    nyttet
    -1.00
    POSITIVE LOGITS
     ママ
    1.05
    hdashline
    1.02
     Cens
    0.97
    Clic
    0.96
    bedienung
    0.94
    neming
    0.92
    ّه
    0.92
     at
    0.90
    ローン
    0.89
     Ще
    0.88
    Activations Density 0.001%

    No Known Activations