© 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. 148011
    Prev
    Next
    INDEX
    Explanations

    stone crusher, busy drawing office

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

    refusal of explicit content

    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
     populist
    0.52
     паліты
    0.50
     politici
    0.50
    公民
    0.48
    archiwizowane
    0.48
    हमें
    0.47
    战
    0.47
     політи
    0.47
    राजनी
    0.47
    왼
    0.46
    POSITIVE LOGITS
     مخصوص
    0.50
     courtyard
    0.48
     الو
    0.47
     recepción
    0.46
     chilled
    0.46
     cake
    0.42
     captivating
    0.42
     pastures
    0.42
     camphor
    0.41
     terroir
    0.41
    Activations Density 0.002%

    No Known Activations