© 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. 143037
    Prev
    Next
    INDEX
    Explanations

    parking near specific locations

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

    structuring or formatting

    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
    ئه
    0.50
    ოტ
    0.48
    سال
    0.48
    ד
    0.47
    などが
    0.47
    пом
    0.46
    食べた
    0.46
    گی
    0.45
     slices
    0.44
    جام
    0.44
    POSITIVE LOGITS
    nd
    0.56
    ant
    0.56
    et
    0.51
    er
    0.50
    te
    0.47
     নেবে
    0.47
     项
    0.47
    eret
    0.46
    ção
    0.46
    ,<
    0.45
    Activations Density 0.000%

    No Known Activations