© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2652
    Prev
    Next
    INDEX
    Explanations

    identifying specific items, types, or features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    0.81
    im
    0.80
     was
    0.73
    羪
    0.73
    (
    0.72
     you
    0.71
    ط
    0.71
     embroiled
    0.70
     sixties
    0.67
     imagination
    0.67
    POSITIVE LOGITS
    ings
    0.85
    ו
    0.80
    are
    0.70
    unde
    0.68
    ą
    0.64
    П
    0.63
    For
    0.63
    detection
    0.62
    d
    0.62
    determine
    0.62
    Activations Density 0.624%

    No Known Activations