© 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. 136770
    Prev
    Next
    INDEX
    Explanations

    sized Princess

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

    message split hacking historically bug

    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
    lim
    0.49
    ura
    0.48
    Pearson
    0.48
    ı
    0.48
    )
    0.47
    }
    0.47
    lima
    0.47
    se
    0.46
    though
    0.46
    ze
    0.46
    POSITIVE LOGITS
     khắp
    0.52
     gonflement
    0.51
     producteurs
    0.50
    ပြင်
    0.49
     ডায়
    0.49
    ၜ
    0.48
     useCallback
    0.47
     productores
    0.47
     wygl
    0.46
     nád
    0.46
    Activations Density 0.001%

    No Known Activations