© 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. 64080
    Prev
    Next
    INDEX
    Explanations

    technical specifications

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

    after list item

    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
     via
    0.50
     劉
    0.47
     तात्पर्य
    0.46
     นัก
    0.46
     contentType
    0.46
     AppComponent
    0.46
    ப்பதற்காக
    0.45
     ചെയ്യാ
    0.45
     createContext
    0.45
    ༻
    0.45
    POSITIVE LOGITS
    omenclature
    0.54
    stitution
    0.45
    diesel
    0.45
    реи
    0.44
    vehicles
    0.44
    windigkeit
    0.44
    pra
    0.43
    population
    0.43
    frak
    0.43
    algebra
    0.43
    Activations Density 0.001%

    No Known Activations