© 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. 243932
    Prev
    Next
    INDEX
    Explanations

    graphics kit, year, half

    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
     Einstellung
    0.55
     integrar
    0.54
    𝓼
    0.54
     Pltf
    0.53
     інте
    0.52
     inscripción
    0.52
    亓
    0.51
     Schell
    0.50
     смартфо
    0.49
     voces
    0.49
    POSITIVE LOGITS
    ib
    0.51
    ↵↵
    0.46
    obj
    0.46
    lad
    0.46
    ij
    0.45
    jir
    0.45
    List
    0.43
    حص
    0.43
    alpha
    0.43
    human
    0.43
    Activations Density 0.001%

    No Known Activations