© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3765
    Prev
    Next
    INDEX
    Explanations

    Units and quantities

    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_16_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
    ;
    0.89
    (
    0.73
    ad
    0.66
    ara
    0.65
    रा
    0.65
    ba
    0.65
     antagonists
    0.65
    ح
    0.64
    bing
    0.63
    ipso
    0.62
    POSITIVE LOGITS
     leur
    0.71
    EN
    0.70
    ко
    0.68
    en
    0.68
    的用户
    0.67
    اقة
    0.65
     அவர்களின்
    0.65
     الى
    0.65
     wordt
    0.65
    ண்ட்
    0.64
    Activations Density 0.579%

    No Known Activations