© 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. 122395
    Prev
    Next
    INDEX
    Explanations

    upcoming, contractual, or mandatory action

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

    understanding user requests

    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
    j
    0.66
    l
    0.54
    t
    0.53
    iced
    0.49
    --
    0.48
     Capacitor
    0.47
    inam
    0.45
     peas
    0.45
    ---
    0.45
    /
    0.45
    POSITIVE LOGITS
     ধরেই
    0.56
     भर्ती
    0.53
     দুর্ঘটনা
    0.52
     સમય
    0.52
     ক্রমশ
    0.52
     आवश्यक
    0.48
     বুঝিতে
    0.48
    多多
    0.47
     Siempre
    0.46
     अनिवार
    0.46
    Activations Density 0.000%

    No Known Activations