© 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. 22-GEMMASCOPE-RES-131K
    7. 36530
    Prev
    Next
    INDEX
    Explanations

    North, page, Loving, XXII

    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
    ueras
    -1.19
    哪儿
    -1.17
     build
    -1.13
     created
    -1.13
    とおり
    -1.09
    ");
    -1.09
    ();
    -1.09
     Geistes
    -1.08
     dział
    -1.07
     medical
    -1.06
    POSITIVE LOGITS
    がありますが
    1.42
    gewöhn
    1.31
     gewo
    1.24
    Interes
    1.18
    Controllo
    1.17
    Klas
    1.15
    ramid
    1.15
    Arty
    1.13
    sproble
    1.13
    Gön
    1.10
    Activations Density 0.065%

    No Known Activations