© 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. 15222
    Prev
    Next
    INDEX
    Explanations

    each corresponding

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

    each corresponding

    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
    URNIZOR
    0.50
    iguë
    0.45
    islang
    0.43
    偃
    0.43
     tarses
    0.42
     hátsó
    0.41
     opérateur
    0.41
    гатьох
    0.41
    暗示
    0.40
     हरित
    0.40
    POSITIVE LOGITS
     each
    0.78
    第
    0.75
     corresponding
    0.74
     Each
    0.69
     EACH
    0.64
     jeweil
    0.62
    each
    0.61
     соответству
    0.61
    对应的
    0.59
    每个
    0.59
    Activations Density 0.010%

    No Known Activations