© 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. 124537
    Prev
    Next
    INDEX
    Explanations

    determining or authority

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

    sql select statements

    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
    ąż
    0.51
    tyw
    0.50
     显示
    0.49
     உன்
    0.47
    olt
    0.46
    ế
    0.46
    贵
    0.46
    ன்த
    0.45
     wyświet
    0.45
    ujourd
    0.45
    POSITIVE LOGITS
     contagion
    0.51
     valence
    0.44
     nonparametric
    0.44
    ГУ
    0.44
    یک
    0.41
     fillets
    0.41
     serre
    0.41
    悚
    0.41
     pointwise
    0.40
    مثل
    0.40
    Activations Density 0.001%

    No Known Activations