© 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. 243886
    Prev
    Next
    INDEX
    Explanations

    square black paintings

    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
    帏
    0.48
     intentos
    0.47
     eventos
    0.46
    iski
    0.46
    㝅
    0.46
    માં
    0.44
    ໃຫ້
    0.44
    级别的
    0.44
     coinChange
    0.44
     tenido
    0.44
    POSITIVE LOGITS
     良
    0.48
     sogenannten
    0.44
     ping
    0.42
     przede
    0.42
    zw
    0.42
    с
    0.42
     square
    0.41
     Swimming
    0.41
     desicc
    0.41
    是很
    0.41
    Activations Density 0.000%

    No Known Activations