© 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. 40380
    Prev
    Next
    INDEX
    Explanations

    author of

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

    time and random calls

    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
     ခ
    0.48
     Television
    0.47
     একটি
    0.44
     Boxing
    0.42
     दूरी
    0.42
     एक
    0.41
     একজনের
    0.41
     Mattress
    0.40
     Talent
    0.40
     ஒருவர்
    0.40
    POSITIVE LOGITS
    中華
    0.50
    等が
    0.47
    Desen
    0.47
    篭
    0.46
    یدر
    0.45
    Ž
    0.45
    Ƙ
    0.44
    bewegung
    0.44
    Scandinavian
    0.44
    ITAS
    0.44
    Activations Density 0.000%

    No Known Activations