© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    fraud protection tokens

    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_29_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
    parser
    0.68
    ৈর
    0.63
    parsed
    0.63
    árd
    0.62
    処理
    0.61
    ﺄ
    0.60
     parsed
    0.60
    rologist
    0.60
     arch
    0.60
    CLR
    0.58
    POSITIVE LOGITS
    waitSeconds
    0.67
     smi
    0.67
    Ids
    0.67
     মিত্র
    0.65
     Cous
    0.61
    coes
    0.60
     setId
    0.60
    㕣
    0.59
    ০০
    0.59
     mjes
    0.59
    Activations Density 0.429%

    No Known Activations