© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200681
    Prev
    Next
    INDEX
    Explanations

    orders, identify, not match

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

    social aspects and reflection

    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
     to
    0.51
     til
    0.46
     internation
    0.45
    噜
    0.45
    git
    0.44
    lympi
    0.44
     Internation
    0.44
     Darstellung
    0.43
     MEET
    0.42
     知
    0.42
    POSITIVE LOGITS
    Provider
    0.50
    Average
    0.50
    Deferred
    0.48
    ક્સ
    0.47
    average
    0.47
    Representative
    0.47
     поверхность
    0.47
    inputSelect
    0.46
    част
    0.46
    Type
    0.45
    Activations Density 0.001%

    No Known Activations