© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 1593
    Prev
    Next
    INDEX
    Explanations

    harm, violation, distress, impairment

    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_9_width_16k_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
     naught
    2.22
     rugged
    1.75
     mesta
    1.67
    ğraf
    1.65
    ཎ
    1.63
     mesons
    1.59
     гало
    1.59
    ﺋ
    1.56
     geld
    1.54
    <unused89>
    1.54
    POSITIVE LOGITS
    at
    1.80
    िल
    1.54
    oc
    1.53
    ち
    1.52
    é
    1.49
    ap
    1.48
    im
    1.47
    and
    1.45
    ис
    1.44
    am
    1.39
    Activations Density 0.404%

    No Known Activations