© 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. 40-GEMMASCOPE-2-RES-262K
    7. 11918
    Prev
    Next
    INDEX
    Explanations

    you can/cannot/should/shouldn't

    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_40_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
     había
    0.44
     avait
    0.42
     возь
    0.42
     Á
    0.40
     avaient
    0.40
     hade
    0.40
     estis
    0.39
    шлось
    0.39
     á
    0.39
     Dazu
    0.39
    POSITIVE LOGITS
     cannot
    0.68
     Cannot
    0.64
    Cannot
    0.63
     нельзя
    0.59
    cannot
    0.57
     CANT
    0.56
     ALWAYS
    0.47
    并不是
    0.46
    也不能
    0.45
    сі
    0.42
    Activations Density 0.006%

    No Known Activations