© 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. 10-GEMMASCOPE-RES-131K
    7. 66465
    Prev
    Next
    INDEX
    Explanations

    v0 followed by version numbers or specific tokens

    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_10/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
    3
    -2.61
    which
    -2.56
    P
    -2.44
    ]
    -2.38
    }
    -2.33
     wich
    -2.14
    S
    -2.05
     geprü
    -2.05
    1
    -2.00
     erfolgre
    -1.95
    POSITIVE LOGITS
    を購入
    2.41
    ânsito
    2.28
    didSet
    2.19
    providedIn
    2.19
     pedir
    2.05
    錞
    2.05
    columnwidth
    2.03
    彼得
    1.98
    怂
    1.95
    ᥬ
    1.92
    Activations Density 0.004%

    No Known Activations