© 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. 163945
    Prev
    Next
    INDEX
    Explanations

    trip and booking

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

    difficult and harmful contexts

    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
     ಮಾನ
    0.54
    詐
    0.54
    ों
    0.52
    長の
    0.51
    Hitting
    0.50
    ITEM
    0.49
    決
    0.48
    表現
    0.47
    問い
    0.47
    ナス
    0.47
    POSITIVE LOGITS
     Reg
    0.57
     sét
    0.55
     Radio
    0.52
     Context
    0.51
     Snack
    0.50
     Opp
    0.50
     Knit
    0.49
     Voices
    0.48
     Refs
    0.48
     bevy
    0.48
    Activations Density 0.000%

    No Known Activations