© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2328
    Prev
    Next
    INDEX
    Explanations

    addictive nature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    й
    1.31
     censure
    1.25
    ма
    1.23
     éclat
    1.22
    вица
    1.21
    י
    1.21
     swords
    1.20
    會有
    1.17
    ין
    1.16
     erupted
    1.14
    POSITIVE LOGITS
    m
    1.63
    unto
    1.38
    est
    1.34
    ur
    1.27
    ary
    1.25
    できる
    1.24
    logging
    1.23
    ২
    1.21
    ic
    1.20
    momentum
    1.19
    Activations Density 0.005%

    No Known Activations