© 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. 182127
    Prev
    Next
    INDEX
    Explanations

    gender analysis, food, politics, faith, personal names, finance

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

    detailed analysis of specific conditions

    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
    с
    0.49
     получается
    0.48
    कों
    0.47
    о
    0.47
    сы
    0.47
    кур
    0.45
    си
    0.44
    пи
    0.44
     રસ
    0.43
    让她
    0.43
    POSITIVE LOGITS
     hydrostatic
    0.56
     Norwich
    0.53
    ):
    0.52
    bounded
    0.51
     any
    0.50
     a
    0.46
     thee
    0.45
    WITH
    0.45
     reclamation
    0.45
     leopard
    0.45
    Activations Density 0.007%

    No Known Activations