© 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. 148145
    Prev
    Next
    INDEX
    Explanations

    natural reflex

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

    child attempting

    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
    उचर
    0.44
     Boltzmann
    0.44
     пул
    0.44
    杨
    0.44
    プリング
    0.43
    াস্থ্য
    0.43
     Boeh
    0.43
     क्विंट
    0.43
    䙲
    0.43
     Wahr
    0.43
    POSITIVE LOGITS
    é
    0.57
     (
    0.49
    str
    0.49
    reng
    0.48
    sing
    0.47
    star
    0.47
    ajan
    0.46
    span
    0.45
    semantics
    0.45
    naj
    0.45
    Activations Density 0.000%

    No Known Activations