© 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. 89828
    Prev
    Next
    INDEX
    Explanations

    legal professionals

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

    configuration, settings, or language

    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
    UNK
    0.48
    摩
    0.46
    DAR
    0.42
    Brooklyn
    0.42
    жал
    0.42
    越南
    0.41
     cleaved
    0.40
    𝕞
    0.40
    ﾟ
    0.40
    ು
    0.39
    POSITIVE LOGITS
     programmi
    0.52
     类型
    0.52
     නිෂ්පා
    0.52
     eigenen
    0.51
     danych
    0.51
     Einstellungen
    0.51
     sicher
    0.51
     eksper
    0.50
     zum
    0.49
     hver
    0.49
    Activations Density 0.001%

    No Known Activations