© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    dates and locations

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

    days and dates

    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
    沉积
    0.44
    鱻
    0.43
     Angeb
    0.43
    别
    0.43
    濑
    0.43
    冯
    0.42
     બે
    0.41
    饰
    0.41
    笕
    0.41
    ीन
    0.41
    POSITIVE LOGITS
    ts
    0.47
    tr
    0.41
    ht
    0.41
    ls
    0.41
    th
    0.40
    rsquo
    0.39
    rs
    0.39
    quot
    0.38
    fac
    0.38
    cite
    0.38
    Activations Density 0.008%

    No Known Activations