© 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-65K
    7. 11154
    Prev
    Next
    INDEX
    Explanations

    whether or if

    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_65k_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
     จำ
    0.52
     overshoot
    0.47
    f
    0.47
     avons
    0.47
     recall
    0.46
     echo
    0.45
    recall
    0.45
    paste
    0.45
    raster
    0.44
     diagonal
    0.44
    POSITIVE LOGITS
    ين
    0.54
    یک
    0.52
     casos
    0.50
    من
    0.47
    ﻝ
    0.47
     fundador
    0.46
    ي
    0.46
    賂
    0.46
    狯
    0.45
    ון
    0.44
    Activations Density 0.006%

    No Known Activations