© 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. 1983
    Prev
    Next
    INDEX
    Explanations

    themes followed by origin or description

    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
    instance
    0.29
    tablet
    0.28
     an
    0.25
     \
    0.25
    Voilà
    0.25
     সুতরাং
    0.24
    ByteArray
    0.24
    O
    0.24
    tooltip
    0.24
    user
    0.24
    POSITIVE LOGITS
     provenant
    0.44
     from
    0.41
     galore
    0.38
     từ
    0.37
    จาก
    0.33
     fromi
    0.32
     från
    0.32
     adicionales
    0.31
     dari
    0.31
     ranging
    0.31
    Activations Density 0.948%

    No Known Activations