© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37853
    Prev
    Next
    INDEX
    Explanations

    it happened

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

    administrative and temporal concepts

    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
    뎀
    0.44
    фо
    0.42
    しています
    0.42
    stri
    0.42
    simplify
    0.41
    7
    0.41
    楽天
    0.41
     древ
    0.41
    Видео
    0.41
    舊
    0.40
    POSITIVE LOGITS
     Attendance
    0.49
     Year
    0.48
     其实
    0.47
     Enrollment
    0.47
     September
    0.47
     Fertil
    0.45
     Inflation
    0.45
     allotted
    0.45
     CAPITAL
    0.45
     Yearly
    0.45
    Activations Density 0.000%

    No Known Activations