© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24907
    Prev
    Next
    INDEX
    Explanations

    runnin' away

    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_all/layer_41_width_262k_l0_big
    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
    鿢
    0.39
    મિત
    0.38
     punya
    0.36
     Dawson
    0.36
    isiaj
    0.36
    เดิน
    0.35
     डिट
    0.35
     IDF
    0.35
    PLF
    0.34
    fonso
    0.34
    POSITIVE LOGITS
    away
    0.61
     away
    0.59
    Away
    0.55
     Away
    0.53
    跑到
    0.52
    跑
    0.52
    奔
    0.51
     AWAY
    0.49
     달려
    0.46
     sprinting
    0.46
    Activations Density 0.002%

    No Known Activations