© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    worn, corrupted, or damaged

    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_22_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
     безопас
    0.77
     ordinateur
    0.70
     вычисли
    0.67
    르고
    0.65
    {``
    0.65
     безо
    0.65
     využ
    0.64
    斤
    0.63
     práv
    0.62
     मंत्रिमंडल
    0.62
    POSITIVE LOGITS
     damaged
    2.02
    damaged
    1.69
     degraded
    1.61
     deteriorated
    1.56
    损坏
    1.55
     broken
    1.53
     damage
    1.53
     क्षतिग्रस्त
    1.51
     decayed
    1.48
     degradation
    1.46
    Activations Density 0.150%

    No Known Activations