© 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. 786
    Prev
    Next
    INDEX
    Explanations

    but introduces contrast

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

    contrasting conjunctions

    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
     ohms
    0.31
     veldig
    0.31
     meinem
    0.31
     veoma
    0.30
    ون
    0.30
     soooo
    0.30
     來
    0.30
     olds
    0.29
     ،
    0.29
     btw
    0.29
    POSITIVE LOGITS
     Procter
    0.29
    随着
    0.27
    Although
    0.26
    记者
    0.26
    A
    0.26
    Despite
    0.25
     усилия
    0.25
    尽管
    0.25
    The
    0.24
    despite
    0.24
    Activations Density 0.497%

    No Known Activations