© 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. 1810
    Prev
    Next
    INDEX
    Explanations

    customs documents, agent, portfolio, dog, data

    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
    𝕖
    0.43
    をはじめ
    0.43
     relatable
    0.38
    ُ
    0.38
    ydın
    0.38
     числа
    0.36
    ęd
    0.36
    ș
    0.36
    état
    0.36
    Issledovatel
    0.36
    POSITIVE LOGITS
     ONLY
    0.49
     Somehow
    0.43
     only
    0.42
     Only
    0.42
     Other
    0.42
     BTW
    0.40
     Frankly
    0.40
     WTF
    0.40
     Unusual
    0.40
     Small
    0.39
    Activations Density 0.000%

    No Known Activations