© 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. 127109
    Prev
    Next
    INDEX
    Explanations

    locations and actions

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

    creating to describe or explain

    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
    km
    0.55
    *
    0.55
     km
    0.54
     kilometers
    0.52
     kilometer
    0.52
     kent
    0.52
     tel
    0.49
     lobes
    0.49
     día
    0.49
     kilomet
    0.49
    POSITIVE LOGITS
    ו
    0.57
    ا
    0.49
    চের
    0.49
    וי
    0.48
    ולי
    0.48
    티
    0.48
    ू
    0.47
    煖
    0.47
    व
    0.47
    わ
    0.47
    Activations Density 0.000%

    No Known Activations