© 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. 9-GEMMASCOPE-2-RES-262K
    7. 10278
    Prev
    Next
    INDEX
    Explanations

    security concepts

    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_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
    d
    3.05
     tej
    2.70
    orithm
    2.65
    ında
    2.65
    人
    2.64
    د
    2.63
     Secondo
    2.61
     somm
    2.57
    𝐎
    2.52
    А
    2.45
    POSITIVE LOGITS
    ি
    3.42
    curité
    2.98
    वानिव
    2.86
    renewcommand
    2.86
     увиде
    2.76
     hundred
    2.68
     луч
    2.67
    pregnant
    2.65
    ieth
    2.61
     unital
    2.58
    Activations Density 0.146%

    No Known Activations