© 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. 84515
    Prev
    Next
    INDEX
    Explanations

    origin or type

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

    financial or professional contexts

    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
    Storyboard
    0.50
    opend
    0.49
    ющимся
    0.49
    Reliance
    0.48
    Corner
    0.45
    郯
    0.45
    Redirect
    0.43
    Strange
    0.43
    莘
    0.43
    Roll
    0.43
    POSITIVE LOGITS
     reducción
    0.59
     mujeres
    0.58
     więcej
    0.55
     riduzione
    0.55
     bleiben
    0.55
     imagens
    0.54
     clashes
    0.54
    ibilidade
    0.54
     versie
    0.54
     electrolytes
    0.53
    Activations Density 0.000%

    No Known Activations