© 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. 218314
    Prev
    Next
    INDEX
    Explanations

    grammatical structures

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

    Russian World, memory, ship

    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
    (
    0.45
     hazard
    0.45
    如此
    0.45
    '
    0.45
     vignette
    0.44
     timeline
    0.43
     বহন
    0.43
     workload
    0.43
     podcast
    0.43
     TAB
    0.42
    POSITIVE LOGITS
     extraño
    0.57
    WeekDates
    0.55
     بالنسب
    0.52
     chieft
    0.52
     священ
    0.50
    thiaz
    0.50
     Estrella
    0.50
     preparando
    0.50
    庥
    0.50
     ､
    0.49
    Activations Density 0.000%

    No Known Activations