© 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. 209842
    Prev
    Next
    INDEX
    Explanations

    legal and medical terms

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

    light direction

    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
    Configure
    0.46
    相似
    0.46
    姑
    0.46
    ﹂
    0.44
    茅
    0.44
    擾
    0.44
    লা
    0.43
    ولو
    0.43
    터
    0.42
    ουσ
    0.42
    POSITIVE LOGITS
    ít
    0.56
    al
    0.55
    _
    0.55
     IgM
    0.53
    u
    0.53
     Ra
    0.52
     for
    0.51
    ress
    0.51
     Ig
    0.51
    eev
    0.50
    Activations Density 0.000%

    No Known Activations