© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75044
    Prev
    Next
    INDEX
    Explanations

    file naming conventions

    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
    ing
    -3.13
    ⸒
    -2.64
    vantaged
    -2.63
    }
    -2.63
    Not
    -2.58
    Also
    -2.52
    Like
    -2.30
    Still
    -2.28
    」、「
    -2.27
    ة
    -2.19
    POSITIVE LOGITS
    摀
    2.63
    ῞
    2.58
     focuses
    2.47
    你
    2.44
     precludes
    2.41
     necesitan
    2.39
    lgari
    2.36
     proble
    2.36
     REALLY
    2.33
    疍
    2.31
    Activations Density 0.076%

    No Known Activations