© 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. 131910
    Prev
    Next
    INDEX
    Explanations

    hair cuts and styles

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

    ** **contact information**

    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
    ன்ப
    0.49
    점으로
    0.48
    J
    0.48
    ونی
    0.46
    jahteraan
    0.46
     depictions
    0.45
    کس
    0.45
    A
    0.45
    ंत्रिक
    0.44
     valuation
    0.43
    POSITIVE LOGITS
     Osbourne
    0.58
     King
    0.52
     Between
    0.51
     Harley
    0.51
     BufferedWriter
    0.49
     Spencer
    0.49
     Woolf
    0.49
     Squirrel
    0.47
     Harry
    0.47
     Jekyll
    0.47
    Activations Density 0.000%

    No Known Activations