© 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-262K
    7. 40005
    Prev
    Next
    INDEX
    Explanations

    src directory paths

    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
    great
    0.52
     ').
    0.45
    Left
    0.45
    choco
    0.45
    不会
    0.45
    ##
    0.44
     Chocolate
    0.44
    四大
    0.44
    <td>
    0.43
    最小
    0.43
    POSITIVE LOGITS
    .”
    0.49
     crescimento
    0.48
     краси
    0.47
     enfermo
    0.47
    。”
    0.46
     apresent
    0.46
     tinham
    0.46
     vhodné
    0.44
     tiveram
    0.44
     prédio
    0.43
    Activations Density 0.013%

    No Known Activations