© 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. 21026
    Prev
    Next
    INDEX
    Explanations

    spanning a period or extent

    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
     într
    0.55
     transportasi
    0.55
     kada
    0.54
     bahwa
    0.54
     beetje
    0.54
     താമസ
    0.54
     도움
    0.53
    Ｃ
    0.53
     qualcosa
    0.52
     aislamiento
    0.52
    POSITIVE LOGITS
    Throughout
    1.19
     Throughout
    1.10
     throughout
    1.05
     suốt
    0.95
    ตลอด
    0.73
    يرا
    0.72
    整个
    0.71
    the
    0.70
    整個
    0.68
    ين
    0.68
    Activations Density 0.012%

    No Known Activations