© 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. 229312
    Prev
    Next
    INDEX
    Explanations

    types of text

    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
    <0x0D>
    0.42
    后续
    0.42
    হীন
    0.40
    ঃ
    0.39
     adhesive
    0.39
    jala
    0.39
    Isolation
    0.39
     写
    0.39
    分离
    0.39
    治
    0.38
    POSITIVE LOGITS
     uffic
    0.54
     tendances
    0.49
    リンク
    0.47
     אחת
    0.47
     limousine
    0.46
     Ruman
    0.45
     بکر
    0.45
     piccola
    0.44
    SUV
    0.44
     avoc
    0.43
    Activations Density 0.000%

    No Known Activations