© 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. 66791
    Prev
    Next
    INDEX
    Explanations

    friction and wave making

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

    popularity and reasons

    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
     cancerous
    0.54
    കാശ
    0.48
    টাল
    0.45
    toluene
    0.44
    Length
    0.44
    畫面
    0.44
    িখ
    0.43
    豢
    0.43
     torre
    0.43
     bistouri
    0.43
    POSITIVE LOGITS
     เพราะ
    0.49
     اخیر
    0.46
     مح
    0.44
     جون
    0.43
     Demokrat
    0.43
     होमवर्क
    0.43
    onesome
    0.41
     COVID
    0.40
     Covid
    0.40
     своими
    0.40
    Activations Density 0.000%

    No Known Activations