© 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. 67144
    Prev
    Next
    INDEX
    Explanations

    data identifiers

    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
    }$
    -3.48
    ’
    -3.06
    enguaje
    -2.19
    A
    -2.17
    硨
    -2.16
    ↵
    -2.14
    vantaged
    -2.11
    It
    -2.09
    {~
    -2.08
    ᠂
    -2.05
    POSITIVE LOGITS
    ၟ
    2.59
    Ἢ
    2.48
    𖤍
    2.44
    <bos>
    2.42
    出來的
    2.34
    
    2.30
    葑
    2.30
    ſu
    2.25
    ஂ
    2.23
    节省
    2.22
    Activations Density 0.001%

    No Known Activations