© 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. 168268
    Prev
    Next
    INDEX
    Explanations

    donations or enjoy

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

    serving kings

    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
    Fot
    0.51
     להיות
    0.50
    Colorful
    0.49
    Работа
    0.48
    Д
    0.46
    Smart
    0.46
    Tiene
    0.46
    С
    0.46
    Hfn
    0.45
    Painter
    0.45
    POSITIVE LOGITS
     mois
    0.49
     bapt
    0.48
     SEN
    0.46
     disc
    0.46
     halv
    0.46
     sj
    0.46
     şeh
    0.46
     TEM
    0.45
     directe
    0.44
     sz
    0.44
    Activations Density 0.000%

    No Known Activations