© 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. 103707
    Prev
    Next
    INDEX
    Explanations

    story continuation

    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
    秾
    -2.06
    筇
    -1.98
     poised
    -1.98
     emite
    -1.96
     you
    -1.88
     been
    -1.82
    咴
    -1.82
    ⻬
    -1.82
    ℟
    -1.81
    
    -1.78
    POSITIVE LOGITS
    '
    2.80
    ↵
    2.47
    .”
    2.30
    t
    2.30
    l
    2.14
    on
    2.06
    na
    2.00
    𓆜
    1.91
    ؛
    1.89
    n
    1.88
    Activations Density 0.003%

    No Known Activations