© 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. 49704
    Prev
    Next
    INDEX
    Explanations

    limits and restrictions

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

    Natural language understanding and speech recognition

    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
     два
    0.55
     totalement
    0.55
     сексуа
    0.55
     fermion
    0.51
     км
    0.48
     сверху
    0.48
     дві
    0.48
     т
    0.47
    か
    0.46
     suivante
    0.46
    POSITIVE LOGITS
     English
    0.54
     planes
    0.51
     Planes
    0.50
     mentored
    0.50
    N
    0.49
    manız
    0.48
     Membranes
    0.46
     Content
    0.46
     Wars
    0.46
     Mainland
    0.46
    Activations Density 0.000%

    No Known Activations