© 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. 25314
    Prev
    Next
    INDEX
    Explanations

    quoted attributes and tags

    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
     just
    -1.66
     only
    -1.58
     those
    -1.51
     by
    -1.46
     often
    -1.45
     not
    -1.44
     people
    -1.44
     so
    -1.44
     five
    -1.42
     six
    -1.41
    POSITIVE LOGITS
     weihnachten
    1.57
    ➢
    1.49
    ╒
    1.46
    küche
    1.45
    during
    1.45
    etwork
    1.42
    MONG
    1.41
    ⓒ
    1.40
    Aç
    1.39
     Sébastien
    1.37
    Activations Density 0.020%

    No Known Activations