© 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. 195089
    Prev
    Next
    INDEX
    Explanations

    specific names and common nouns

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

    just after bullet points

    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
    比如
    0.46
     például
    0.44
    凌晨
    0.44
    例如
    0.43
    ’
    0.43
    軟件
    0.42
     появится
    0.42
     esimerkiksi
    0.42
     například
    0.41
    يران
    0.41
    POSITIVE LOGITS
    nds
    0.62
     whenever
    0.49
    lying
    0.47
     arba
    0.47
     screwing
    0.45
    죵
    0.45
     indented
    0.45
     धन
    0.44
     sillas
    0.44
     کیوں
    0.44
    Activations Density 0.001%

    No Known Activations