© 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. 123707
    Prev
    Next
    INDEX
    Explanations

    receive them

    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
    спользование
    0.52
    据
    0.49
    क्रोस
    0.49
    лектро
    0.48
    ając
    0.48
     આજ
    0.47
    वरील
    0.46
    𝚊
    0.46
    ट्रोल
    0.46
    海外
    0.45
    POSITIVE LOGITS
     precludes
    0.59
     preclude
    0.57
     precluded
    0.50
     collective
    0.49
     morphology
    0.44
     periphery
    0.44
     morphologies
    0.44
     coalesce
    0.44
     subgroups
    0.44
     phenotypic
    0.43
    Activations Density 0.009%

    No Known Activations