© 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. 46698
    Prev
    Next
    INDEX
    Explanations

    was winter, I get

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

    `.` and `,` commands

    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
     เค
    0.52
     rf
    0.46
     reactants
    0.46
     ૧
    0.45
     RF
    0.44
    rf
    0.43
    RF
    0.43
    ad
    0.43
    aca
    0.43
     δύο
    0.42
    POSITIVE LOGITS
    ﺓ
    0.51
    ändig
    0.49
    밤
    0.48
    趣
    0.45
    verständlich
    0.45
    граммы
    0.43
    之为
    0.43
    트는
    0.42
     weihn
    0.41
    役割
    0.41
    Activations Density 0.000%

    No Known Activations