© 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. 73918
    Prev
    Next
    INDEX
    Explanations

    ability or possibility

    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
    錞
    -3.27
    "
    -2.72
     katk
    -2.64
     peut
    -2.63
     tabak
    -2.56
    },
    -2.50
    didn
    -2.44
     beru
    -2.42
     verhind
    -2.36
     необходимые
    -2.36
    POSITIVE LOGITS
    <bos>
    2.86
    之前的
    2.45
     resolute
    2.30
    淦
    2.09
     exquisitely
    2.09
    酒屋
    2.06
     conceptually
    2.03
     After
    2.03
    嘯
    2.02
     psychotic
    2.00
    Activations Density 0.001%

    No Known Activations