© 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. 31619
    Prev
    Next
    INDEX
    Explanations

    signing below

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

    business or technical applications

    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
     单
    0.47
     实现
    0.46
    )=(
    0.45
     Parameters
    0.44
     Starring
    0.44
     )\
    0.43
    )=[
    0.42
    0
    0.42
     tcp
    0.42
    联网
    0.42
    POSITIVE LOGITS
     phony
    0.53
     immaculate
    0.50
     falso
    0.47
    adero
    0.46
     opulent
    0.46
    abbat
    0.45
     neglect
    0.45
     represent
    0.44
     homology
    0.44
    記述
    0.44
    Activations Density 0.000%

    No Known Activations