© 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. 187720
    Prev
    Next
    INDEX
    Explanations

    financial institutionssubstance use disordersimilarities betweeneast coastcardsloop

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

    much better

    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
    И
    0.57
    ud
    0.54
    ("
    0.53
    اس
    0.52
    ب
    0.52
    o
    0.50
     владе
    0.50
    خ
    0.50
    [{
    0.49
    q
    0.49
    POSITIVE LOGITS
    日から
    0.47
     persever
    0.46
     hauled
    0.46
     remorse
    0.45
     singles
    0.45
     bisog
    0.45
    ریٹر
    0.44
     perseverance
    0.44
    誓
    0.43
     tarjeta
    0.42
    Activations Density 0.000%

    No Known Activations