© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 142077
    Prev
    Next
    INDEX
    Explanations

    money, bills, and plans

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

    explaining AI reasoning

    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
     indústria
    0.55
    ங்கோ
    0.53
    ディスプレイ
    0.49
    麺
    0.49
    વાની
    0.47
    ומ
    0.46
    韓
    0.45
     DISPLAYS
    0.44
    広く
    0.44
    ឥត
    0.44
    POSITIVE LOGITS
     
    0.49
     Bibliography
    0.49
     Review
    0.47
     Wills
    0.47
     McKinney
    0.47
     Writer
    0.46
     Marquette
    0.46
    avier
    0.46
     Bass
    0.46
     Paralympic
    0.46
    Activations Density 0.000%

    No Known Activations