© 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. 126361
    Prev
    Next
    INDEX
    Explanations

    song title disambiguation

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

    abbreviations and technical terms

    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
     우리가
    0.43
     নিরী
    0.42
    迸
    0.42
     неприят
    0.38
    されて
    0.38
    不仅
    0.38
    ศี
    0.37
     кою
    0.37
     ভয়ানক
    0.37
    NOT
    0.37
    POSITIVE LOGITS
     tiež
    0.45
     otherwise
    0.44
     see
    0.44
     See
    0.43
    ...@
    0.43
     Ayrıca
    0.42
    なども
    0.42
     Alaska
    0.42
    also
    0.41
    ...),
    0.41
    Activations Density 0.005%

    No Known Activations