© 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. 243990
    Prev
    Next
    INDEX
    Explanations

    action leading to outcome

    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
    珈
    0.50
    陀
    0.47
    ᅪ
    0.46
     পূর্ব
    0.46
    循
    0.44
     間
    0.44
    constrained
    0.44
    ダイ
    0.43
    戍
    0.43
    未知
    0.43
    POSITIVE LOGITS
     tweaks
    0.49
     jedna
    0.46
     brainstorm
    0.45
     administers
    0.45
     sesize
    0.45
     participate
    0.44
     ellos
    0.43
     لاحظوا
    0.43
     discharges
    0.43
     discapac
    0.43
    Activations Density 0.003%

    No Known Activations