© 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. 160754
    Prev
    Next
    INDEX
    Explanations

    endocrine disrupting compound

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

    escalating incidents

    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
     імен
    0.49
     викона
    0.43
     vykon
    0.42
    査
    0.41
    Plist
    0.41
    ว่าเป็น
    0.40
     яких
    0.40
    真
    0.40
     Sentiment
    0.40
    attributes
    0.40
    POSITIVE LOGITS
     nasz
    0.48
     confianza
    0.47
     déjà
    0.46
     Nights
    0.46
     überras
    0.45
     discurso
    0.45
     gana
    0.45
     nights
    0.43
     deja
    0.43
     அதிகரிக்கும்
    0.42
    Activations Density 0.001%

    No Known Activations