© 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. 242674
    Prev
    Next
    INDEX
    Explanations

    temple, occupied, mouths

    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
    ર્મા
    0.47
    固
    0.44
     удовле
    0.44
    bpm
    0.43
     сиз
    0.42
    Д
    0.42
     disapproved
    0.42
    高度
    0.41
     intang
    0.41
    aterally
    0.41
    POSITIVE LOGITS
     Religion
    0.51
     २०
    0.46
     Fell
    0.45
     町
    0.45
    izing
    0.45
     Cluj
    0.44
     Montevideo
    0.44
     Nek
    0.44
     Jr
    0.42
     বাড়িতে
    0.42
    Activations Density 0.002%

    No Known Activations