© 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. 76765
    Prev
    Next
    INDEX
    Explanations

    average baby

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

    open weights versus open source

    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
    6
    0.56
    igm
    0.51
    ik
    0.49
    wym
    0.49
     j
    0.49
    Bo
    0.48
     J
    0.48
    ៦
    0.48
    wahl
    0.47
    ek
    0.46
    POSITIVE LOGITS
     استاذ
    0.51
    ربی
    0.48
    тельства
    0.48
     cane
    0.47
    participants
    0.47
     pathway
    0.46
    раз
    0.46
     scholarship
    0.46
     بخشی
    0.45
    跛
    0.45
    Activations Density 0.000%

    No Known Activations