© 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. 160540
    Prev
    Next
    INDEX
    Explanations

    events or statements about futures

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

    accurate predictions

    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
    ट
    0.55
    ką
    0.52
    s
    0.52
    ஸ்
    0.51
    SPORT
    0.50
    एम
    0.49
    klin
    0.49
    J
    0.49
    FIT
    0.48
    MATH
    0.48
    POSITIVE LOGITS
     vilá
    0.57
     glow
    0.48
     Glowing
    0.48
     Veranstaltungen
    0.47
     აღმასრულ
    0.46
     glowing
    0.45
     länger
    0.45
     wereld
    0.44
    amless
    0.43
     probing
    0.43
    Activations Density 0.000%

    No Known Activations