© 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. 8595
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios

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

    if, hypothetical, conditional

    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
    انة
    0.45
     exag
    0.45
    任意の
    0.45
     piles
    0.44
     farce
    0.44
     ones
    0.43
    讀
    0.42
     proves
    0.42
    ونة
    0.42
    ב
    0.42
    POSITIVE LOGITS
     сейчас
    0.52
     discontinued
    0.44
     вместо
    0.44
     verschiedene
    0.44
     TODAY
    0.44
    instead
    0.44
    하시
    0.43
     गईं
    0.43
     এখনই
    0.42
     оптима
    0.41
    Activations Density 0.020%

    No Known Activations