© 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. 40726
    Prev
    Next
    INDEX
    Explanations

    in accordance, receive customized, based on

    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
     `$
    0.41
    Config
    0.40
    Digital
    0.40
    Dtos
    0.39
     أق
    0.39
    Arquivo
    0.38
    ාවක්
    0.38
     aliments
    0.38
     ఫ
    0.38
     odnos
    0.38
    POSITIVE LOGITS
     ponieważ
    0.48
    шкан
    0.46
     nourrir
    0.46
    ustrated
    0.44
     karena
    0.44
    ieb
    0.42
    urgie
    0.42
    于
    0.42
    於
    0.42
     upang
    0.42
    Activations Density 0.010%

    No Known Activations