© 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. 74381
    Prev
    Next
    INDEX
    Explanations

    years old, free mail, web services

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

    web presentation windows mother

    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
    𝚆
    0.52
     dopiero
    0.48
     przen
    0.47
     comenc
    0.46
     cannab
    0.46
     agron
    0.46
     препарат
    0.46
     gahet
    0.45
    neighbor
    0.45
     অর্চনা
    0.45
    POSITIVE LOGITS
    起
    0.49
     बचना
    0.42
     Gior
    0.40
    義
    0.39
     मृत्यू
    0.38
    槸
    0.38
    底下
    0.38
     ನಿ
    0.37
     सिंग
    0.37
    粱
    0.36
    Activations Density 0.000%

    No Known Activations