© 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. 158533
    Prev
    Next
    INDEX
    Explanations

    website uses and data collection

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

    website uses cookies and GitHub

    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
     我們
    0.44
    OFF
    0.43
    食事
    0.43
     ইন্টারনেট
    0.41
     限
    0.40
     壁
    0.40
    寶寶
    0.40
    限
    0.40
    )。
    0.39
    吃飯
    0.39
    POSITIVE LOGITS
     Morav
    0.48
    ղ
    0.45
     oppos
    0.44
     Ministers
    0.43
     Lot
    0.42
     commentators
    0.42
     commentaries
    0.42
     papers
    0.41
     ministers
    0.41
     Citro
    0.41
    Activations Density 0.010%

    No Known Activations