© 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. 164288
    Prev
    Next
    INDEX
    Explanations

    dessert or fruit names

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

    RC Circuit or Risk Identification

    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
     wäre
    0.59
    ėtų
    0.57
     hoje
    0.56
     mädchen
    0.55
     conteúdo
    0.53
     छात्रा
    0.53
    ḿ
    0.52
     ezt
    0.52
    dyž
    0.52
     vorige
    0.52
    POSITIVE LOGITS
     cannons
    0.55
    りと
    0.54
     dishes
    0.48
     cannon
    0.47
     communications
    0.47
    cannon
    0.47
    ي
    0.47
     transducers
    0.46
    かの
    0.45
     protectors
    0.45
    Activations Density 0.001%

    No Known Activations