© 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. 132831
    Prev
    Next
    INDEX
    Explanations

    about things or ideas

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

    Gemma team

    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
    financing
    0.56
    linkOpacity
    0.55
    sourceIP
    0.52
    iziModal
    0.52
    GetAsyncKeyState
    0.52
    comparing
    0.52
    ceedings
    0.52
    🅻
    0.51
    cookbook
    0.50
    Databaze
    0.50
    POSITIVE LOGITS
     To
    0.46
     Pick
    0.46
     Hernandez
    0.45
     It
    0.44
     Ment
    0.43
     Conj
    0.43
     Ü
    0.42
     Anaheim
    0.42
     Catania
    0.42
    长沙
    0.42
    Activations Density 0.000%

    No Known Activations