© 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. 10-GEMMASCOPE-RES-131K
    7. 128576
    Prev
    Next
    INDEX
    Explanations

    using or by followed by specific methods

    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
     then
    -1.52
     notori
    -1.37
     ATTORNEY
    -1.30
    椟
    -1.26
    vowel
    -1.23
     eventually
    -1.20
     Violon
    -1.20
    only
    -1.20
     suddenly
    -1.19
    basically
    -1.19
    POSITIVE LOGITS
     besonderen
    1.43
     beeintr
    1.36
    理由は
    1.36
     the
    1.32
     beherr
    1.26
     musíte
    1.23
     rouse
    1.20
     erneu
    1.20
    ”,
    1.17
    Katar
    1.17
    Activations Density 0.287%

    No Known Activations