© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 7312
    Prev
    Next
    INDEX
    Explanations

    a descriptive adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    anych
    0.50
    the
    0.48
    a
    0.46
    The
    0.45
    to
    0.45
    các
    0.44
    and
    0.43
     sebagainya
    0.41
    ;
    0.41
     autres
    0.41
    POSITIVE LOGITS
     veritable
    0.69
     simple
    0.68
     delightful
    0.67
     whopping
    0.66
     blatant
    0.64
     cornerstone
    0.64
     poignant
    0.63
     subtle
    0.63
     sneaky
    0.63
     hefty
    0.62
    Activations Density 1.489%

    No Known Activations