© 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. 44
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

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

    explaining steps or instructions

    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
     monomial
    0.20
     （
    0.19
    льбе
    0.19
     geophysical
    0.19
     morphisms
    0.18
     wasser
    0.18
     anzeigen
    0.18
    راحی
    0.18
    \
    0.18
     dexterity
    0.18
    POSITIVE LOGITS
     It
    0.22
    It
    0.22
    There
    0.21
    if
    0.20
    there
    0.19
     it
    0.19
     даже
    0.19
    They
    0.19
    私は
    0.18
     большинство
    0.18
    Activations Density 0.206%

    No Known Activations