© 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. 5080
    Prev
    Next
    INDEX
    Explanations

    phrases following specific words

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

    descriptive titles and labels

    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
    Yard
    0.44
     పుష్
    0.44
    +}$,
    0.44
    犯
    0.42
    NodeType
    0.41
     gravel
    0.40
    *",
    0.40
     kaca
    0.40
    UB
    0.39
     conjunto
    0.39
    POSITIVE LOGITS
    しょ
    0.54
    те
    0.48
    協
    0.47
    ப்பட
    0.47
    ギー
    0.47
    pregnancy
    0.47
    translation
    0.47
    エ
    0.46
    іл
    0.46
    ле
    0.46
    Activations Density 0.000%

    No Known Activations