© 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. 239021
    Prev
    Next
    INDEX
    Explanations

    salvation, distress, contact, equipment

    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
    ाइन
    0.48
    녓
    0.44
    ıyordu
    0.43
     버전
    0.43
     배경
    0.42
    нето
    0.42
    тер
    0.41
    物質
    0.41
    несен
    0.41
     Verfahren
    0.41
    POSITIVE LOGITS
    !
    0.50
     potencia
    0.45
     seulement
    0.43
     senhores
    0.42
     l
    0.42
    2
    0.42
     ↓
    0.41
    ming
    0.41
    ؟!
    0.41
     Ridge
    0.40
    Activations Density 0.001%

    No Known Activations