© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95774
    Prev
    Next
    INDEX
    Explanations

    historical context and further details

    np_acts-logits-general · gemini-2.5-flash-lite

    physical or abstract problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tā
    0.59
     jî
    0.59
     ní
    0.54
     wooded
    0.54
     initio
    0.53
    َهُ
    0.53
     selatan
    0.52
     minimax
    0.51
     manz
    0.50
     gourd
    0.48
    POSITIVE LOGITS
     exclusivement
    0.54
    稼
    0.46
    历史上
    0.45
    ாளர்க
    0.44
    ဂျ
    0.43
    发
    0.42
    援
    0.42
    ープ
    0.42
    پ
    0.42
    合物
    0.42
    Activations Density 0.001%

    No Known Activations