© 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. 185748
    Prev
    Next
    INDEX
    Explanations

    ex girlfriend

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

    presented as requested

    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
    cijas
    0.49
    겅
    0.49
    द्दल
    0.48
    atsiooni
    0.47
    authentication
    0.46
    ابر
    0.46
    치는
    0.46
    insuku
    0.45
     conecta
    0.43
    kommt
    0.43
    POSITIVE LOGITS
     Wessex
    0.48
     (
    0.45
     deprived
    0.44
     город
    0.43
     büy
    0.43
    WY
    0.43
    REACTOR
    0.42
     Quỳnh
    0.42
     remarked
    0.42
     град
    0.42
    Activations Density 0.000%

    No Known Activations