© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 299
    Prev
    Next
    INDEX
    Explanations

    copy and paste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     kass
    1.35
     mắt
    1.32
    cenik
    1.31
    习近平
    1.31
    ẩm
    1.31
     Odisha
    1.30
    ☚
    1.28
    ventus
    1.27
    的风
    1.27
    Nexus
    1.27
    POSITIVE LOGITS
    9
    0.86
    arl
    0.84
    ift
    0.82
    1
    0.81
     Coolidge
    0.75
    opub
    0.73
    Wt
    0.72
    8
    0.72
    raw
    0.72
    ocol
    0.71
    Activations Density 0.081%

    No Known Activations