© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90809
    Prev
    Next
    INDEX
    Explanations

    actions and consequences

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

    safety goals and loss scenarios

    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
    Negative Logits
    କ
    0.53
     teachers
    0.52
    ન્સ
    0.49
     soltanto
    0.49
    Το
    0.48
    mor
    0.48
    ində
    0.48
    我是
    0.47
    square
    0.47
    る
    0.47
    POSITIVE LOGITS
     첨
    0.48
     విశ
    0.45
     Dat
    0.45
    LLO
    0.45
     Xuân
    0.44
     تمر
    0.44
     عباس
    0.44
     เชื่อ
    0.43
    柽
    0.42
     Springfield
    0.42
    Activations Density 0.000%

    No Known Activations