© 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-65K
    7. 772
    Prev
    Next
    INDEX
    Explanations

    numbers preceding Riverside or punctuation

    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
     fine
    0.48
     g
    0.48
     sm
    0.47
     increasingly
    0.46
     overwhelming
    0.45
     threat
    0.44
     running
    0.43
     st
    0.42
     sh
    0.42
     good
    0.41
    POSITIVE LOGITS
    ૦
    0.77
    ૯
    0.72
     ಅಥವಾ
    0.65
    Cliente
    0.64
     અને
    0.64
    <unused1745>
    0.63
    mAh
    0.63
     รวม
    0.62
    ۰
    0.62
     teléfono
    0.62
    Activations Density 0.346%

    No Known Activations