© 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. 18104
    Prev
    Next
    INDEX
    Explanations

    essentially deterministic state

    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
     první
    0.44
    িয়াছে
    0.41
     første
    0.39
     beforeDir
    0.39
    îtier
    0.39
    틸
    0.39
     eerste
    0.38
     الجديدة
    0.38
     thử
    0.38
     اہم
    0.38
    POSITIVE LOGITS
    reducing
    0.44
    |.
    0.44
    dys
    0.43
    ).
    0.43
    rate
    0.43
    Reduce
    0.42
    reduce
    0.42
    per
    0.41
    fix
    0.40
    weighted
    0.40
    Activations Density 0.000%

    No Known Activations