© 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. 24-GEMMASCOPE-2-RES-262K
    7. 5757
    Prev
    Next
    INDEX
    Explanations

    do not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
     somewhat
    0.45
     which
    0.44
    -
    0.43
     might
    0.41
    /
    0.40
     the
    0.40
     could
    0.39
     a
    0.38
     pourrait
    0.38
     since
    0.37
    POSITIVE LOGITS
    轻易
    0.57
    任何人
    0.48
    偪
    0.45
    以外
    0.45
    凌
    0.44
    欺
    0.44
     केवल
    0.41
    逞
    0.40
    仠
    0.40
     শুধু
    0.39
    Activations Density 0.059%

    No Known Activations