© 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. 89790
    Prev
    Next
    INDEX
    Explanations

    enforcement officials

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

    abuse and harm

    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
    
    0.52
     незале
    0.49
    мм
    0.48
    맇
    0.46
    🇫
    0.45
     ім
    0.45
    Académie
    0.45
    intégr
    0.45
     синх
    0.45
    𝐦
    0.45
    POSITIVE LOGITS
     sustancias
    0.51
     afirma
    0.47
    कारात्मक
    0.47
     drinks
    0.44
     buscando
    0.44
     pessoas
    0.44
     bottled
    0.44
     sterilized
    0.43
     bebidas
    0.43
     stimulant
    0.43
    Activations Density 0.000%

    No Known Activations