© 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-16K
    7. 6754
    Prev
    Next
    INDEX
    Explanations

    type names and concepts

    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_16k_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
     মহাশয়ের
    0.54
    ☼
    0.54
     ∫
    0.51
     shortcoming
    0.51
    owna
    0.50
    Astronom
    0.50
     GTI
    0.49
    Ꮻ
    0.49
     WoW
    0.49
    Duel
    0.48
    POSITIVE LOGITS
     viande
    0.59
     chiam
    0.57
     bleue
    0.56
     priprav
    0.55
     chiamato
    0.52
     localidad
    0.52
     modelli
    0.50
     cozinha
    0.50
     nombrado
    0.49
    对接
    0.48
    Activations Density 1.166%

    No Known Activations