© 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. 753
    Prev
    Next
    INDEX
    Explanations

    high demand or protein

    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
    ak
    2.16
    et
    2.03
     построе
    2.02
    ut
    1.98
    ta
    1.97
    AD
    1.97
    d
    1.91
    AY
    1.91
    INCREMENT
    1.88
    ING
    1.84
    POSITIVE LOGITS
    brow
    1.95
    ສຸດ
    1.87
     avven
    1.78
    な
    1.76
    で
    1.65
     ז
    1.59
    ς
    1.59
     זאת
    1.58
    てください
    1.57
    ंका
    1.55
    Activations Density 0.217%

    No Known Activations