© 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. 34-GEMMASCOPE-RES-131K
    4. 81380
    Prev
    Next
    INDEX
    Explanations

    questions and technical terms

    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_34/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
    Im
    -0.81
    ゴ
    -0.81
    協會
    -0.80
    >
    -0.79
    ])]
    -0.78
    Do
    -0.75
     Geschenk
    -0.75
    }-
    -0.73
    }>\
    -0.73
     old
    -0.71
    POSITIVE LOGITS
    diensten
    0.84
    ンドン
    0.83
    rô
    0.83
     Sejarah
    0.83
    ोजन
    0.82
     formel
    0.80
     TEND
    0.80
    küche
    0.78
     fondamental
    0.78
     Arquivado
    0.78
    Activations Density 0.000%

    No Known Activations