© 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. 150061
    Prev
    Next
    INDEX
    Explanations

    places, offers

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

    AVC curve, Human Algorithm, trial

    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
    ח
    0.51
     тер
    0.49
    ១
    0.48
    تر
    0.48
    ح
    0.47
     mixtures
    0.47
    ش
    0.47
     ون
    0.46
     مه
    0.46
     обще
    0.46
    POSITIVE LOGITS
     Entscheidung
    0.47
     relocate
    0.42
     NEP
    0.41
     criar
    0.41
     आपल्याला
    0.41
     depositors
    0.40
     NETWORK
    0.40
     Euler
    0.39
    yyum
    0.39
    ρικ
    0.39
    Activations Density 0.000%

    No Known Activations