© 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. 4908
    Prev
    Next
    INDEX
    Explanations

    eye contact, eye-catching

    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
     arterios
    1.10
     опро
    1.04
     適
    1.04
     élo
    1.00
    ratulations
    0.97
     ergonomics
    0.97
     artística
    0.96
    তম
    0.95
     irony
    0.95
     elasticity
    0.90
    POSITIVE LOGITS
    л
    1.03
    adic
    1.02
    eye
    1.01
    atts
    0.98
     glaucoma
    0.98
    眶
    0.97
    ild
    0.97
    Date
    0.97
     cornea
    0.97
     barrels
    0.93
    Activations Density 0.030%

    No Known Activations