© 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. 71880
    Prev
    Next
    INDEX
    Explanations

    getting the message

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

    offers and explanations

    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
    巉
    0.46
    喍
    0.45
    ڡ
    0.45
    こだわ
    0.44
    秙
    0.43
    从此
    0.43
    ન્દ
    0.43
    findpost
    0.42
     cifra
    0.41
    逅
    0.40
    POSITIVE LOGITS
    chen
    0.53
    systems
    0.49
    sys
    0.47
    pt
    0.46
    SYSTEM
    0.46
    S
    0.45
     systems
    0.45
    io
    0.44
    ami
    0.44
    dimensional
    0.43
    Activations Density 0.000%

    No Known Activations