© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129151
    Prev
    Next
    INDEX
    Explanations

    text-align

    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_22/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
    などが
    -1.85
    は
    -1.61
    もあって
    -1.54
    と
    -1.53
    が
    -1.52
    があり
    -1.51
    もありますが
    -1.50
     এবং
    -1.50
    もある
    -1.49
     of
    -1.48
    POSITIVE LOGITS
    為に
    1.63
    ところに
    1.55
    When
    1.44
    _
    1.33
     tijden
    1.32
    ことも
    1.27
     soorten
    1.27
    Some
    1.23
    んですよ
    1.23
    ようです
    1.22
    Activations Density 0.004%

    No Known Activations