© 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. 62396
    Prev
    Next
    INDEX
    Explanations

    quantifier + noun/suffix

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

    observing unexpected situations

    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
    k
    0.55
    refer
    0.53
    cite
    0.52
    glBind
    0.46
    akaranam
    0.46
    bk
    0.45
    úde
    0.45
    íns
    0.45
    is
    0.44
    idot
    0.44
    POSITIVE LOGITS
     considérable
    0.48
     sillons
    0.47
     নীতির
    0.46
     পদক্ষেপ
    0.45
    یا
    0.45
    瓦
    0.43
    ну
    0.43
    恶
    0.42
     étude
    0.42
    过来
    0.42
    Activations Density 0.000%

    No Known Activations