© 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. 123589
    Prev
    Next
    INDEX
    Explanations

    past work, cost, relationship types

    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
     பிரி
    0.49
     thác
    0.46
     polygons
    0.44
     olig
    0.42
     五
    0.41
     同时
    0.41
     向
    0.40
    wnież
    0.40
     သည်
    0.39
     simult
    0.39
    POSITIVE LOGITS
    irma
    0.52
    ър
    0.48
    พ
    0.47
     posao
    0.46
    פ
    0.46
     paycheck
    0.46
     legitimately
    0.45
     खासा
    0.45
    経験
    0.43
    Honestly
    0.43
    Activations Density 0.006%

    No Known Activations