© 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. 5247
    Prev
    Next
    INDEX
    Explanations

    proper nouns and non-English items

    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
     cyclic
    0.51
     `=`
    0.49
     abiotic
    0.48
     an
    0.48
     geomet
    0.47
     feces
    0.47
     kilograms
    0.46
     mucous
    0.46
     texture
    0.46
     monoton
    0.46
    POSITIVE LOGITS
    esque
    0.63
    などの
    0.60
    II
    0.60
    etc
    0.60
    I
    0.60
     etc
    0.58
    などが
    0.58
     등이
    0.57
    など
    0.56
     প্রমুখ
    0.55
    Activations Density 0.054%

    No Known Activations