© 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. 227617
    Prev
    Next
    INDEX
    Explanations

    Sabbath and Monday

    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
    ган
    0.54
    TEE
    0.52
    ம்ம
    0.50
    дача
    0.49
    "_
    0.48
    emplacement
    0.48
    мены
    0.47
     ム
    0.47
    щением
    0.47
    埬
    0.47
    POSITIVE LOGITS
     coaching
    0.51
     axon
    0.51
     axial
    0.49
     presiding
    0.49
     inflation
    0.46
     locomotion
    0.46
     ocean
    0.46
     avalanche
    0.46
     nickel
    0.46
     fish
    0.45
    Activations Density 0.001%

    No Known Activations