© 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. 207052
    Prev
    Next
    INDEX
    Explanations

    django models and pytest

    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
    紀錄
    0.46
     Account
    0.44
     Mark
    0.43
    Mark
    0.43
    㐰
    0.42
    Accounts
    0.41
    忽然
    0.41
    洙
    0.40
    owi
    0.40
     Tem
    0.40
    POSITIVE LOGITS
     chromatography
    0.51
     chromatographic
    0.49
     adsor
    0.48
     photometric
    0.47
     flammable
    0.47
     immersive
    0.46
     heterogeneity
    0.46
     carcinogenic
    0.46
     paramagnetic
    0.46
     nonparametric
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.