© 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. 186791
    Prev
    Next
    INDEX
    Explanations

    prints, Bar, cleanser, swim, dependency

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

    originated in or from

    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
     اثنين
    0.53
    둔
    0.49
    ށ
    0.46
     confounded
    0.46
     устойчи
    0.45
     إلا
    0.44
     остав
    0.44
     сколько
    0.43
    اريات
    0.43
    ثنين
    0.43
    POSITIVE LOGITS
    Sprintf
    0.54
     Minas
    0.50
    onomi
    0.49
    ernes
    0.48
     Neon
    0.48
    ussa
    0.48
    R
    0.48
     Torino
    0.47
     rappresenta
    0.47
    inata
    0.47
    Activations Density 0.000%

    No Known Activations