© 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. 193245
    Prev
    Next
    INDEX
    Explanations

    legal and names

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

    Proper nouns and foreign script

    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
    ות
    0.50
    ní
    0.48
    mehr
    0.47
    盆
    0.46
    бре
    0.45
     stimmen
    0.45
    nehmen
    0.44
    onha
    0.44
    )=
    0.44
     عندي
    0.44
    POSITIVE LOGITS
     Connor
    0.46
     Jill
    0.45
    abank
    0.45
     TimeSpan
    0.44
     পাকিস্তানে
    0.43
     Watertown
    0.43
    ኋ
    0.42
    ப்படாத
    0.42
    జీ
    0.42
    CreateTable
    0.41
    Activations Density 0.001%

    No Known Activations