© 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. 139383
    Prev
    Next
    INDEX
    Explanations

    time and conditions

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

    specific actions given conditions

    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
     což
    0.49
     interpersonal
    0.46
    並且
    0.45
    ↪
    0.45
     ہے۔
    0.45
     něj
    0.45
    าม
    0.45
    。(
    0.45
     হইতেছে
    0.44
    與
    0.44
    POSITIVE LOGITS
     habíamos
    0.60
     habían
    0.59
     avaient
    0.58
     astonished
    0.55
     avevano
    0.55
     hadde
    0.54
     assembled
    0.53
     had
    0.53
    had
    0.52
    assembled
    0.51
    Activations Density 0.000%

    No Known Activations