© 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. 236143
    Prev
    Next
    INDEX
    Explanations

    condition or state

    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
    でした
    0.47
    再次
    0.46
    ח
    0.46
    ור
    0.45
    ਖ
    0.45
    gh
    0.44
     देम
    0.44
    ק
    0.44
    様々な
    0.44
    ಾಗಿತ್ತು
    0.44
    POSITIVE LOGITS
     übrigens
    0.51
     takže
    0.49
     যেহেতু
    0.48
     آینده
    0.47
     phenytoin
    0.47
     totiž
    0.45
     hiszen
    0.44
     dadurch
    0.43
     mivel
    0.43
     حتى
    0.42
    Activations Density 0.001%

    No Known Activations