© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77429
    Prev
    Next
    INDEX
    Explanations

    TRUE or FALSE statements

    np_acts-logits-general · gemini-2.5-flash-lite

    Tokens that are part of mathematical expressions, operators, or numerical values in computational or problem-solving contexts, particularly in examples involving arithmetic operations, comparisons, or code snippets.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04
    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
    照顧
    0.39
     Fair
    0.38
     ზ
    0.38
     tarda
    0.38
    Fair
    0.37
    mere
    0.37
    Fancy
    0.36
     voorz
    0.36
     playerData
    0.36
     Fancy
    0.35
    POSITIVE LOGITS
     falsch
    0.47
    Assertion
    0.46
    认知
    0.45
     inversion
    0.44
     assertion
    0.44
    assertTrue
    0.43
     !=
    0.43
    ativistic
    0.43
     invertible
    0.42
     redefined
    0.42
    Activations Density 0.090%

    No Known Activations