© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39912
    Prev
    Next
    INDEX
    Explanations

    literal and other versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    5
    0.50
     and
    0.48
    1
    0.48
     (
    0.45
     Punch
    0.44
    ch
    0.44
     or
    0.44
     -
    0.43
    BAL
    0.43
    ↵↵
    0.43
    POSITIVE LOGITS
    ほどの
    0.47
    㕷
    0.46
     இருப்பதால்
    0.46
    iança
    0.45
    远的
    0.45
    犃
    0.45
    யர்
    0.44
    跄
    0.44
    鐟
    0.44
    ದಿಂದ
    0.44
    Activations Density 0.002%

    No Known Activations