© 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. 86261
    Prev
    Next
    INDEX
    Explanations

    right or left directions

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

    suggestions or instructions

    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
    𝗖
    0.52
    Υ
    0.48
    𝗛
    0.48
     正規
    0.45
    企業の
    0.44
    Մ
    0.44
    उप
    0.43
    𝗢
    0.43
    鍗
    0.43
     ประเทศ
    0.42
    POSITIVE LOGITS
    ille
    0.49
    geke
    0.49
     tau
    0.48
     sätt
    0.48
     sbagli
    0.47
     gebaut
    0.46
     hanno
    0.46
     sulle
    0.46
     .
    0.45
     mittens
    0.44
    Activations Density 0.000%

    No Known Activations