© 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. 99258
    Prev
    Next
    INDEX
    Explanations

    diseases and problems

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

    distinctions and contrasts

    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
    anía
    0.46
    iss
    0.44
    continued
    0.44
    heni
    0.44
    ний
    0.43
    é
    0.43
    বি
    0.43
    ąg
    0.43
    A
    0.43
    ro
    0.43
    POSITIVE LOGITS
     enfermedades
    0.59
     haya
    0.54
     douleurs
    0.52
     fenómenos
    0.52
     явления
    0.52
     problemi
    0.50
     amarilla
    0.50
     enfermedad
    0.50
     ຫຼື
    0.50
     காரணமாக
    0.50
    Activations Density 0.000%

    No Known Activations