© 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. 10833
    Prev
    Next
    INDEX
    Explanations

    constantly shifting, evolving

    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
     言
    0.53
     зах
    0.49
     ко
    0.48
     хло
    0.47
     plum
    0.46
    rients
    0.46
     gelecek
    0.46
    uellement
    0.45
    舝
    0.45
    ղ
    0.44
    POSITIVE LOGITS
     econôm
    0.48
    ത്താ
    0.47
    로
    0.47
     obligé
    0.46
    </strong>
    0.46
    Professor
    0.46
    야
    0.45
    Sep
    0.44
    也许
    0.44
    보
    0.44
    Activations Density 0.003%

    No Known Activations