© 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. 210602
    Prev
    Next
    INDEX
    Explanations

    Diversity Vision

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

    AI and engineering aspects

    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
    Fa
    0.50
    प्रकाश
    0.47
    ;</
    0.46
    د
    0.44
    む
    0.44
    कांक्षा
    0.43
    O
    0.43
    依然
    0.42
    క్య
    0.42
    意
    0.42
    POSITIVE LOGITS
     partout
    0.52
     பண்ண
    0.46
     legger
    0.46
     harnessed
    0.46
    iewicz
    0.45
     harness
    0.45
     commencer
    0.44
     використову
    0.44
     હજાર
    0.44
     മുത
    0.44
    Activations Density 0.001%

    No Known Activations