© 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. 234247
    Prev
    Next
    INDEX
    Explanations

    Facebook starts, Hindi, between

    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
     मातर
    0.53
    ၁
    0.47
    ahiye
    0.47
     स्वातंत्र
    0.46
     능
    0.46
    ágoras
    0.46
     عظیم
    0.46
     بولی
    0.46
    뒤
    0.45
    është
    0.45
    POSITIVE LOGITS
     Tired
    0.48
     зим
    0.47
     Seasons
    0.46
    Law
    0.45
     Tire
    0.45
     Weil
    0.45
     Sib
    0.43
     Gött
    0.43
     tired
    0.42
     Kreis
    0.42
    Activations Density 0.000%

    No Known Activations