© 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. 32236
    Prev
    Next
    INDEX
    Explanations

    personal injury lawyer, legal, financial, management

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

    writing, applications, important

    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
    ӵ
    0.51
    ωνα
    0.45
    氚
    0.43
    最後まで
    0.43
    дай
    0.40
    ઠા
    0.39
    uge
    0.39
    各種
    0.39
    漬
    0.39
    adah
    0.39
    POSITIVE LOGITS
     eqn
    0.57
     හැ
    0.52
     modernes
    0.51
     erste
    0.51
     archiv
    0.50
     ආරක්ෂ
    0.50
     interdiscipl
    0.50
     arbit
    0.50
     cory
    0.49
     capi
    0.48
    Activations Density 0.000%

    No Known Activations