© 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. 123213
    Prev
    Next
    INDEX
    Explanations

    work week

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

    miles

    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
    פתח
    0.55
    ATING
    0.54
    нев
    0.50
    䔧
    0.49
    ᒡ
    0.48
    ЕЛ
    0.48
    ㄵ
    0.48
    學生
    0.48
    вин
    0.47
    ЕР
    0.47
    POSITIVE LOGITS
     Fax
    0.49
    _
    0.44
     Preference
    0.41
     нами
    0.41
     Automobile
    0.41
    یکن
    0.40
     Preferences
    0.40
     fax
    0.39
     утра
    0.39
     lengths
    0.39
    Activations Density 0.000%

    No Known Activations