© 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. 132436
    Prev
    Next
    INDEX
    Explanations

    Non-English characters or code snippets

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

    about *

    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
     About
    0.51
     Vara
    0.49
     Theatre
    0.49
     Dating
    0.48
     过
    0.48
     University
    0.47
     Symposium
    0.47
     During
    0.47
     calculadora
    0.47
     I
    0.46
    POSITIVE LOGITS
     erroneously
    0.53
    확
    0.49
    ="
    0.47
    Результа
    0.47
    SequentialGroup
    0.46
     opposit
    0.45
    ">−</
    0.45
    ил
    0.44
    ผล
    0.43
    characteristics
    0.43
    Activations Density 0.000%

    No Known Activations