© 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. 162888
    Prev
    Next
    INDEX
    Explanations

    Queen, IEEE, T.B.N.H.Q

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

    incitement to violence

    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
     అన్న
    0.55
    篒
    0.54
     फ्रॉम
    0.51
     కార్డు
    0.51
    🫤
    0.51
     சுண்ணா
    0.50
     देवा
    0.50
     عصر
    0.49
     herramient
    0.49
    denes
    0.48
    POSITIVE LOGITS
    k
    0.60
    B
    0.57
    N
    0.55
    T
    0.54
    Queen
    0.51
    BUT
    0.51
    q
    0.50
    H
    0.50
    IEEE
    0.49
     canopy
    0.49
    Activations Density 0.001%

    No Known Activations