© 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. 52252
    Prev
    Next
    INDEX
    Explanations

    immediate actions and outcomes

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

    immediate impact or response

    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
    🦳
    0.68
    ing
    0.64
    pielt
    0.62
    UM
    0.61
     لحد
    0.61
    UKA
    0.60
     αντί
    0.59
     sám
    0.59
     ಈಗಾಗಲೇ
    0.59
    ä
    0.57
    POSITIVE LOGITS
     imedi
    1.19
    immediate
    1.13
     inmediata
    1.13
     Immediately
    1.12
    immediately
    1.11
     immedi
    1.09
    ทัน
    1.09
     immediately
    1.08
     immédi
    1.08
     Immediate
    1.08
    Activations Density 0.032%

    No Known Activations