© 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. 128830
    Prev
    Next
    INDEX
    Explanations

    crime reporters

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

    grim and dark premises

    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
    ט
    0.45
     diploid
    0.42
     impuls
    0.41
     gland
    0.39
    irano
    0.39
     ორგან
    0.39
    땄
    0.38
     getUser
    0.38
     circumstellar
    0.38
    কারী
    0.38
    POSITIVE LOGITS
     JESUS
    0.52
     दुर्
    0.51
    stieg
    0.51
     Jamboree
    0.46
    ឃ
    0.46
     kriminal
    0.46
     volo
    0.46
    百科
    0.45
    なります
    0.44
     Tween
    0.44
    Activations Density 0.000%

    No Known Activations