© 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. 134381
    Prev
    Next
    INDEX
    Explanations

    care and conditions

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

    examples and usage

    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
     Харків
    0.51
    壕
    0.48
     قطر
    0.45
    واه
    0.44
     localised
    0.43
    ров
    0.43
     použit
    0.42
    ністю
    0.42
     بالن
    0.41
    فق
    0.41
    POSITIVE LOGITS
    k
    0.64
    c
    0.57
    aların
    0.55
     }}^{\
    0.54
    alarının
    0.52
    एनएल
    0.49
    ilize
    0.48
    ılan
    0.48
     変
    0.48
     Awakening
    0.48
    Activations Density 0.001%

    No Known Activations