© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    such terms and conditions

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

    per month, entire Mac, holding tools

    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
     prayed
    0.50
     metallic
    0.47
     definite
    0.45
     hearts
    0.44
     thwarted
    0.43
     mcg
    0.43
     burned
    0.42
     =
    0.41
     Saber
    0.41
     originated
    0.40
    POSITIVE LOGITS
    dü
    0.61
    ആര്‍
    0.61
    gramModel
    0.59
    ä
    0.56
     projek
    0.55
     proses
    0.54
     yüksek
    0.54
    樖
    0.53
    لیکن
    0.53
    slidesPer
    0.52
    Activations Density 0.000%

    No Known Activations