© 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. 11476
    Prev
    Next
    INDEX
    Explanations

    certainty or known facts

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

    what is

    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
    をはじめ
    0.37
     extravag
    0.36
    🧞
    0.34
     தனது
    0.33
     sizlerle
    0.33
     furent
    0.33
    Interestingly
    0.33
     компонен
    0.32
     undergoes
    0.32
    などで
    0.32
    POSITIVE LOGITS
    b
    0.34
    ko
    0.33
     idd
    0.32
    kw
    0.31
     nix
    0.31
    ai
    0.31
    pi
    0.31
    os
    0.30
     k
    0.30
    钾
    0.30
    Activations Density 0.861%

    No Known Activations