© 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. 104353
    Prev
    Next
    INDEX
    Explanations

    mobile banking

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

    offering help or options

    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
    絞
    0.48
    λεί
    0.46
    罌
    0.43
    лия
    0.42
    ва
    0.41
    қа
    0.41
     větš
    0.41
    მ
    0.40
    姹
    0.40
    罂
    0.39
    POSITIVE LOGITS
     stepfather
    0.48
     انگل
    0.47
     stoff
    0.46
     پدر
    0.46
     instinctively
    0.45
     وانا
    0.44
     اوپر
    0.44
     مفید
    0.44
     க்
    0.44
     بج
    0.43
    Activations Density 0.001%

    No Known Activations