© 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. 24-GEMMASCOPE-2-RES-262K
    7. 4219
    Prev
    Next
    INDEX
    Explanations

    AI-powered, style, based

    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_24_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
    比べて
    0.50
    ǵ
    0.49
     einzel
    0.49
     ergibt
    0.45
     überzeugt
    0.45
    🧢
    0.44
     excret
    0.44
    価
    0.44
    <unused23>
    0.43
     specializing
    0.43
    POSITIVE LOGITS
    based
    0.53
    like
    0.49
    in
    0.49
    ary
    0.49
    powered
    0.47
    w
    0.47
    d
    0.45
    n
    0.44
    style
    0.44
    OS
    0.44
    Activations Density 0.072%

    No Known Activations