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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22956
    Prev
    Next
    INDEX
    Explanations

    idiomatic rules and instructions

    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
    m
    0.91
    t
    0.84
    ش
    0.82
    d
    0.76
     ""
    0.72
    i
    0.72
    s
    0.72
     née
    0.70
    म
    0.70
     TTL
    0.69
    POSITIVE LOGITS
    Rules
    1.34
    rules
    1.32
     rules
    1.26
    Rule
    1.24
    rule
    1.23
     규칙
    1.22
    规则
    1.20
     Rules
    1.16
    ルール
    1.11
    RULES
    1.05
    Activations Density 0.030%

    No Known Activations