© 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. 129182
    Prev
    Next
    INDEX
    Explanations

    credit application forms

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

    authenticating aadhaar details or competition

    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
    耔
    0.56
    بعاد
    0.52
     precludes
    0.50
     andDevice
    0.49
     szükség
    0.49
     dve
    0.48
     jedynie
    0.47
     betracht
    0.46
     deser
    0.46
     původ
    0.46
    POSITIVE LOGITS
     It
    0.52
    SP
    0.45
    //
    0.44
    0
    0.43
    ST
    0.43
    df
    0.42
     centric
    0.42
    This
    0.42
    It
    0.41
    AN
    0.41
    Activations Density 0.001%

    No Known Activations