© 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. 77218
    Prev
    Next
    INDEX
    Explanations

    dimensions or measurements

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

    take over the world

    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
    Each
    0.55
    the
    0.52
     the
    0.52
    خدم
    0.50
    I
    0.49
    ki
    0.48
    The
    0.48
    Clark
    0.47
    G
    0.46
    Who
    0.46
    POSITIVE LOGITS
     confund
    0.46
     respiratoires
    0.44
     diferenciar
    0.43
    ofacial
    0.43
     그래서
    0.43
     carbure
    0.43
     ট্যাবলেট
    0.42
    setData
    0.42
     tangga
    0.42
    obeb
    0.41
    Activations Density 0.000%

    No Known Activations