© 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. 172990
    Prev
    Next
    INDEX
    Explanations

    understanding service details NJ

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

    depends on what you need

    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
    tml
    0.52
    ត្រូ
    0.51
     krát
    0.47
    髓
    0.44
    ڀ
    0.43
     思っ
    0.43
    頁
    0.43
    婦
    0.43
    ப்புற
    0.42
    msup
    0.42
    POSITIVE LOGITS
    오
    0.58
     우
    0.55
     오
    0.49
     하나의
    0.49
    YA
    0.49
    의
    0.48
    웨
    0.48
    우
    0.46
     영상
    0.43
    kowe
    0.43
    Activations Density 0.000%

    No Known Activations