© 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. 62503
    Prev
    Next
    INDEX
    Explanations

    word sequences and their continuations

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

    definitions and specific terms

    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
    al
    0.71
    atual
    0.53
    Atual
    0.52
    id
    0.52
    um
    0.51
    ar
    0.49
    ó
    0.48
     Bonus
    0.48
    ليل
    0.48
    il
    0.47
    POSITIVE LOGITS
     외
    0.51
     radiographs
    0.51
    㦣
    0.50
     bushes
    0.50
     interfaces
    0.50
     synchrotron
    0.49
     여
    0.47
     convexity
    0.46
     mappings
    0.46
     pausing
    0.46
    Activations Density 0.000%

    No Known Activations