© 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. 128720
    Prev
    Next
    INDEX
    Explanations

    way out or meets depression

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

    True or False statements

    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
    栞
    0.40
    Kenya
    0.40
     Fulbright
    0.40
    avigation
    0.40
    签署
    0.38
    云南
    0.38
     diversity
    0.38
    削除
    0.38
    Sums
    0.37
    僵
    0.37
    POSITIVE LOGITS
     ομά
    0.49
     irresistible
    0.49
    iče
    0.48
     ""`
    0.48
    станции
    0.46
    ή
    0.45
    يين
    0.45
    alogy
    0.44
    পাড়া
    0.44
    akiem
    0.44
    Activations Density 0.000%

    No Known Activations