© 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. 96647
    Prev
    Next
    INDEX
    Explanations

    foreign words, names, or specific identifiers

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

    interpretation, political cycles, technical terms

    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
     bumped
    0.52
     кола
    0.51
     яка
    0.50
    fal
    0.47
     但
    0.47
     لأنه
    0.46
     उठ
    0.45
    pèce
    0.45
     对
    0.45
    bumps
    0.44
    POSITIVE LOGITS
     Gaj
    0.54
     bildir
    0.47
     zaht
    0.46
    ار
    0.44
     Zimmermann
    0.43
    ශ්‍ය
    0.43
     Biraz
    0.43
     Gifford
    0.43
     Verlauf
    0.42
     Lent
    0.42
    Activations Density 0.001%

    No Known Activations