© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 979
    Prev
    Next
    INDEX
    Explanations

    asymmetry, volatile, coherent

    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
    いた
    1.70
    ிறது
    1.65
    тка
    1.58
    ılabilir
    1.55
    ton
    1.55
     fragen
    1.55
    گاه
    1.51
    𝘨
    1.51
    ah
    1.49
    ductory
    1.48
    POSITIVE LOGITS
    א
    1.56
    "];
    1.40
    飥
    1.35
    TEXTURE
    1.25
    Lett
    1.25
    THE
    1.23
    NOT
    1.23
    populations
    1.23
    ⼤
    1.23
    httphttps
    1.23
    Activations Density 0.283%

    No Known Activations