© 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. 246093
    Prev
    Next
    INDEX
    Explanations

    estate grounds and past tense

    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
    ريب
    0.49
    গিত
    0.48
    QS
    0.47
    음
    0.46
     tenement
    0.46
    जत
    0.46
     Pending
    0.46
    ಲೋ
    0.45
    ارم
    0.45
     निकलते
    0.45
    POSITIVE LOGITS
     いう
    0.48
     Babcock
    0.45
     yǔ
    0.44
     เข้า
    0.43
     トー
    0.42
    ŭ
    0.42
    ön
    0.41
    iał
    0.41
    što
    0.41
    issau
    0.41
    Activations Density 0.001%

    No Known Activations