© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119003
    Prev
    Next
    INDEX
    Explanations

    times and temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <td>
    -1.79
    S
    -1.68
    J
    -1.44
     clothes
    -1.40
    完成后
    -1.38
    of
    -1.35
     either
    -1.35
    ﾘ
    -1.34
     famous
    -1.34
    redientes
    -1.34
    POSITIVE LOGITS
    毟
    1.43
    ㌘
    1.41
    cić
    1.41
     idi
    1.39
    Ḧ
    1.34
     aussit
    1.32
     officielle
    1.32
     őket
    1.31
    ┇
    1.31
    Cpt
    1.30
    Activations Density 0.274%

    No Known Activations