© 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. 64368
    Prev
    Next
    INDEX
    Explanations

    salad prep

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

    often, sometimes

    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
    E
    0.47
    N
    0.45
     clergyman
    0.42
    phony
    0.42
    現在
    0.41
    canada
    0.41
    C
    0.41
    北大
    0.41
    めん
    0.40
     charitable
    0.40
    POSITIVE LOGITS
     GoPro
    0.47
     吴
    0.47
     Warhammer
    0.46
     หมด
    0.46
     Ouvrard
    0.46
     esport
    0.45
     absur
    0.45
     Coefficient
    0.44
     Realme
    0.44
     avem
    0.44
    Activations Density 0.000%

    No Known Activations