© 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. 125996
    Prev
    Next
    INDEX
    Explanations

    requirements and best to find the

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

    financial literacy and migration

    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
     declar
    0.54
    punctuation
    0.46
     irrit
    0.46
    t
    0.46
    х
    0.46
     pendiente
    0.45
    aqua
    0.45
    hid
    0.45
     ciento
    0.44
     及
    0.44
    POSITIVE LOGITS
     පරි
    0.43
     Photographer
    0.43
     Collaborative
    0.42
    迅
    0.42
     cellSize
    0.41
     fastest
    0.41
     traslad
    0.41
    ulang
    0.41
     račun
    0.41
     Balashov
    0.41
    Activations Density 0.000%

    No Known Activations