© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8431
    Prev
    Next
    INDEX
    Explanations

    exact point or answer

    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_65k_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
    ஹீ
    0.76
     তু
    0.75
    నా
    0.73
     exámenes
    0.71
    瘍
    0.71
    蔔
    0.71
     eğer
    0.70
     denominators
    0.70
    う
    0.69
    ће
    0.69
    POSITIVE LOGITS
     elusive
    0.88
    érateur
    0.82
    same
    0.78
    itude
    0.78
    कृपया
    0.77
    ClrType
    0.77
    strength
    0.76
    acidade
    0.76
    ✾
    0.74
    cvt
    0.74
    Activations Density 0.000%

    No Known Activations