© 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. 98868
    Prev
    Next
    INDEX
    Explanations

    here in, by bus, dental microwear

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

    code structures and programming

    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
    軽量
    0.50
    linde
    0.49
    tell
    0.47
    та
    0.47
    v
    0.46
    като
    0.45
     DISCLAIMED
    0.45
    の内
    0.44
     ,
    0.44
    などが
    0.43
    POSITIVE LOGITS
    اتب
    0.46
     chó
    0.46
     Park
    0.45
     বলল
    0.45
    రిగి
    0.45
    çam
    0.43
     Burma
    0.42
    యంలో
    0.42
    হাম্ম
    0.42
     Watergate
    0.42
    Activations Density 0.000%

    No Known Activations