© 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. 91676
    Prev
    Next
    INDEX
    Explanations

    foreign words or phrases

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

    offering potentially dangerous information

    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
    γ
    0.49
     ij
    0.43
     β
    0.42
    acterial
    0.42
     beams
    0.42
     subsequent
    0.42
    nivers
    0.41
     embryonic
    0.41
     overlooks
    0.41
     xii
    0.41
    POSITIVE LOGITS
    פרי
    0.49
     Марафон
    0.48
     önce
    0.46
     finanzi
    0.46
     Ді
    0.45
    쾌
    0.45
     tendances
    0.45
     facilité
    0.45
    촐
    0.45
    Survivor
    0.44
    Activations Density 0.001%

    No Known Activations