© 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. 37241
    Prev
    Next
    INDEX
    Explanations

    entity followed by descriptor

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

    AI, security, analytics, finance, bills

    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
    8
    0.48
    6
    0.46
    ٥
    0.46
    ٨
    0.45
    7
    0.43
    ٦
    0.43
    9
    0.41
    5
    0.41
    4
    0.39
    ۸
    0.38
    POSITIVE LOGITS
    䀼
    0.30
    ä
    0.30
    ización
    0.29
    w
    0.29
    Punk
    0.29
    筤
    0.29
    ለያዩ
    0.29
     होके
    0.29
     from
    0.28
     জন্য
    0.28
    Activations Density 0.058%

    No Known Activations