© 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. 89613
    Prev
    Next
    INDEX
    Explanations

    Scanner, received, recently, may, dust, acquire

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

    welcome, sampling, copied

    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
     s
    0.52
     m
    0.48
     salted
    0.47
     d
    0.46
     nbsp
    0.46
     pancreatic
    0.46
     photography
    0.44
    xam
    0.44
     sympathy
    0.44
    密码
    0.44
    POSITIVE LOGITS
    য়া
    0.46
    দিষ্ট
    0.45
    پوینت
    0.42
    ATP
    0.41
    ڠ
    0.40
     Produto
    0.39
     Año
    0.39
    ட்ப
    0.39
    YEAR
    0.39
    Levi
    0.39
    Activations Density 0.000%

    No Known Activations