© 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. 80584
    Prev
    Next
    INDEX
    Explanations

    examples, years, talking

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

    financial transactions and data processing

    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
    ذلك
    0.50
     iccad
    0.49
     stärker
    0.48
     necesitaba
    0.48
    👘
    0.47
    🕯
    0.46
    CodeableConcept
    0.46
    ٨
    0.46
    ฟัง
    0.46
    ப்பட்டது
    0.46
    POSITIVE LOGITS
    iler
    0.51
     out
    0.47
    XXX
    0.47
     invest
    0.46
    observ
    0.46
    ļa
    0.46
    zoom
    0.46
     Zoom
    0.45
    un
    0.45
    isu
    0.45
    Activations Density 0.001%

    No Known Activations