© 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. 11369
    Prev
    Next
    INDEX
    Explanations

    word following specific terms

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

    lists of categories and qualifiers

    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
    。
    0.48
    מ
    0.44
     bibli
    0.42
     nonprofits
    0.42
    ברו
    0.41
     ethnicities
    0.41
    examples
    0.40
     debates
    0.40
     opposites
    0.40
    like
    0.39
    POSITIVE LOGITS
    gifter
    0.52
    ierung
    0.49
    ociação
    0.48
     নায়ক
    0.48
     మైసూరు
    0.47
    🈚
    0.47
     reducción
    0.47
     କ
    0.46
    ólito
    0.46
     রাধানাথ
    0.46
    Activations Density 0.000%

    No Known Activations