© 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. 7170
    Prev
    Next
    INDEX
    Explanations

    words connecting ideas

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

    conjunctions and contrasts

    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
    ،
    0.34
     jednotliv
    0.33
    »،
    0.29
    "،
    0.29
    
    0.29
    ”،
    0.28
     kroppen
    0.28
    '،
    0.28
     katika
    0.27
     sním
    0.27
    POSITIVE LOGITS
    and
    0.45
     and
    0.44
    which
    0.42
     which
    0.40
     এবং
    0.39
    but
    0.39
    所以我
    0.39
    if
    0.39
     so
    0.39
     и
    0.39
    Activations Density 1.098%

    No Known Activations