© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 109534
    Prev
    Next
    INDEX
    Explanations

    hand / room / the same

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

    guitar intro

    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
    ٹنے
    0.51
    rizioni
    0.47
    Ũ
    0.44
     dramas
    0.43
     杨
    0.43
    oje
    0.43
    nikiem
    0.43
    ;")
    0.42
     naszej
    0.42
    ffi
    0.42
    POSITIVE LOGITS
    ᄁ
    0.46
    כז
    0.46
    綑
    0.45
    ᱫ
    0.44
    aluminum
    0.44
    يطان
    0.43
    牆
    0.43
    kale
    0.42
     weiteres
    0.42
    बॉलीवुड
    0.42
    Activations Density 0.000%

    No Known Activations