© 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. 225834
    Prev
    Next
    INDEX
    Explanations

    URLs and context

    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
    TTLE
    0.52
    FilesIn
    0.48
    യുടെ
    0.48
     المصفوفه
    0.46
     abbrevi
    0.46
    }}}+\
    0.45
     את
    0.45
    iyu
    0.44
    యి
    0.44
    氤
    0.43
    POSITIVE LOGITS
    〃
    0.49
    odynamics
    0.46
     pow
    0.45
    ibank
    0.44
     merchandising
    0.44
     hutan
    0.44
    保管
    0.44
    apas
    0.43
    awt
    0.43
    etor
    0.42
    Activations Density 0.001%

    No Known Activations