© 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. 97815
    Prev
    Next
    INDEX
    Explanations

    voting, numbers, findings, interface, coming

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

    terms of service

    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
     両
    0.51
    とっても
    0.50
    これは
    0.49
     これは
    0.48
    というのは
    0.46
     Detta
    0.45
    because
    0.45
     積
    0.44
    んです
    0.44
     ಇದನ್ನು
    0.44
    POSITIVE LOGITS
     onboarding
    0.75
     podcasts
    0.65
     fintech
    0.64
     metaverse
    0.63
     webinars
    0.62
     infrastrukt
    0.60
     DevOps
    0.59
     podcast
    0.57
     incentiv
    0.57
     diaspora
    0.57
    Activations Density 0.002%

    No Known Activations