© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 730
    Prev
    Next
    INDEX
    Explanations

    TAG followed by configuration

    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
     예술
    1.06
     화
    1.01
     heartfelt
    1.00
     endearing
    0.99
     Refunds
    0.99
     핵
    0.99
     beggars
    0.97
     paradox
    0.97
     갑
    0.97
     Gaul
    0.97
    POSITIVE LOGITS
    this
    0.93
    Math
    0.89
    new
    0.88
    Constant
    0.88
    get
    0.84
    tilde
    0.82
    Region
    0.82
    the
    0.82
    B
    0.80
    P
    0.80
    Activations Density 0.735%

    No Known Activations