© 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. 150294
    Prev
    Next
    INDEX
    Explanations

    establishing stability

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

    attributing blame or 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
    צ
    0.55
    ਵਾ
    0.51
    дут
    0.49
    𝚛
    0.49
    کن
    0.49
    وا
    0.48
     услови
    0.48
    ﺟ
    0.47
     говорили
    0.47
    GLOB
    0.47
    POSITIVE LOGITS
     Err
    0.53
     Montgomery
    0.50
     Swing
    0.50
     Medizin
    0.49
     Moisture
    0.49
     Fusion
    0.48
     Taipei
    0.47
     Municipality
    0.46
     Nano
    0.46
     Circuit
    0.46
    Activations Density 0.000%

    No Known Activations