© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    datasets, crime, divine, sustainability, code

    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
     قوانین
    0.46
    atti
    0.45
    ėti
    0.44
     આવ
    0.43
    贓
    0.43
     ایران
    0.43
     académicos
    0.43
     alumina
    0.43
     относи
    0.42
     તપાસ
    0.42
    POSITIVE LOGITS
     Penny
    0.51
     Map
    0.51
    𝔹
    0.50
     Soul
    0.49
     Data
    0.48
     böl
    0.48
     Region
    0.47
     Lease
    0.46
     Throw
    0.45
     Pix
    0.45
    Activations Density 0.001%

    No Known Activations