© 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. 10-GEMMASCOPE-RES-131K
    7. 128271
    Prev
    Next
    INDEX
    Explanations

    user home directory paths

    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
     schuhe
    -1.60
     küche
    -1.58
     estiver
    -1.56
     verborgen
    -1.54
    ЛЬ
    -1.54
     verminder
    -1.51
     bescha
    -1.47
    英寸
    -1.46
     verhind
    -1.45
    】【
    -1.45
    POSITIVE LOGITS
    }
    1.71
    ;
    1.65
     "..\..\
    1.64
    ’
    1.54
     who
    1.53
    isait
    1.49
    ?”
    1.45
     zuletzt
    1.43
     včetně
    1.43
    ya
    1.38
    Activations Density 0.013%

    No Known Activations