© 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. 225725
    Prev
    Next
    INDEX
    Explanations

    languages and official roles

    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
     disposit
    0.45
    쪽
    0.45
     منف
    0.44
    ям
    0.42
    represented
    0.42
    անակ
    0.42
    ast
    0.42
    것도
    0.41
    icut
    0.40
    schein
    0.40
    POSITIVE LOGITS
    Months
    0.54
     riusc
    0.51
    DEN
    0.50
    Officials
    0.50
     Journalist
    0.49
    ᱑
    0.49
     Londra
    0.49
     eighty
    0.48
    Leggi
    0.48
     sindaco
    0.48
    Activations Density 0.001%

    No Known Activations