© 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. 47925
    Prev
    Next
    INDEX
    Explanations

    types of

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

    word emphasis

    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
    z
    0.42
    cha
    0.39
    $_{
    0.38
     berichtet
    0.38
    ppled
    0.38
     Std
    0.38
    ructive
    0.37
    unin
    0.37
    hle
    0.37
     whispered
    0.36
    POSITIVE LOGITS
     και
    0.47
     અને
    0.45
     والأ
    0.44
     and
    0.44
    ས
    0.43
     ו
    0.42
    菌
    0.42
     fabricación
    0.42
     এবং
    0.40
    SERVATION
    0.40
    Activations Density 0.000%

    No Known Activations