© 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. 10646
    Prev
    Next
    INDEX
    Explanations

    academic publications

    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
     for
    -2.42
    },
    -2.22
     are
    -2.17
    ."
    -2.05
     in
    -2.02
    "
    -2.02
    ("
    -1.95
    ),
    -1.92
     was
    -1.85
     /
    -1.78
    POSITIVE LOGITS
    嚨
    2.02
    Ꮉ
    2.00
     チラシ
    1.98
    ⩤
    1.98
    CurtirCurtir
    1.98
    狆
    1.96
    蹓
    1.96
     髪型
    1.95
    浤
    1.95
     camiset
    1.94
    Activations Density 0.010%

    No Known Activations