© 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. 12-GEMMASCOPE-2-RES-262K
    7. 4220
    Prev
    Next
    INDEX
    Explanations

    buy something

    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_12_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
    IONAL
    1.96
    }"]
    1.91
     abol
    1.86
    voud
    1.83
     stools
    1.78
     commutes
    1.72
    巅
    1.71
    mical
    1.70
    ዎት
    1.70
     riport
    1.68
    POSITIVE LOGITS
    и
    2.42
    го
    2.31
    е
    2.17
    о
    2.14
    idade
    2.13
    <0x80>
    2.06
    ité
    2.02
    ి
    1.98
    ism
    1.97
    до
    1.96
    Activations Density 0.055%

    No Known Activations