© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111789
    Prev
    Next
    INDEX
    Explanations

    size of stores and costs

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence endings and new sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exhibitors
    0.45
    class
    0.44
     internal
    0.44
    HOUSE
    0.44
    s
    0.43
    internal
    0.42
    类的
    0.42
    फ्ते
    0.42
    USERS
    0.42
     podamos
    0.42
    POSITIVE LOGITS
    raisal
    0.57
    emia
    0.48
     stemming
    0.46
     Wikipedia
    0.44
    所得
    0.44
    }_{
    0.43
    recht
    0.43
     Ashram
    0.43
    yaratan
    0.42
    .~
    0.42
    Activations Density 0.001%

    No Known Activations