© 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. 98939
    Prev
    Next
    INDEX
    Explanations

    automated import and export

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

    parametric analysis

    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
     ముందుకు
    0.46
    rowser
    0.46
    ប្រស
    0.46
     Langevin
    0.45
     Tracking
    0.44
    వారు
    0.44
    ల్యే
    0.44
    ༅
    0.43
     personen
    0.43
     Narendra
    0.43
    POSITIVE LOGITS
    ربه
    0.55
    大切
    0.46
    screenshots
    0.45
    cale
    0.45
    πέ
    0.44
     investimento
    0.44
    evice
    0.44
     illustrious
    0.43
    enemies
    0.43
     тем
    0.43
    Activations Density 0.000%

    No Known Activations