© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1327
    Prev
    Next
    INDEX
    Explanations

    am

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    罌
    0.55
     F
    0.54
    F
    0.52
    вик
    0.50
    Ｆ
    0.49
    ฟ
    0.49
    戽
    0.49
     হানি
    0.47
    夗
    0.47
     ฟ
    0.47
    POSITIVE LOGITS
     CO
    0.53
    ogr
    0.52
     cod
    0.48
    asto
    0.48
    ocol
    0.47
    CO
    0.46
    oct
    0.46
    CODES
    0.45
    gt
    0.45
     NgModule
    0.44
    Activations Density 0.121%

    No Known Activations