© 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. 69878
    Prev
    Next
    INDEX
    Explanations

    console commands

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

    granting, serious, securely, ladder

    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
     ç
    0.55
     seiner
    0.49
     systems
    0.49
     offenbar
    0.47
     (
    0.47
     и
    0.46
     c
    0.45
     unter
    0.45
    PRNewswire
    0.44
     O
    0.43
    POSITIVE LOGITS
    Salah
    0.62
    Mim
    0.52
    MaxSize
    0.51
    വേഷ
    0.50
    LZ
    0.50
    SqlCommand
    0.49
     patham
    0.49
    isola
    0.49
    NAS
    0.48
    BackgroundHelper
    0.47
    Activations Density 0.000%

    No Known Activations