© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11286
    Prev
    Next
    INDEX
    Explanations

    documentation says

    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
     デニム
    -1.05
    Svet
    -1.03
    Stolen
    -1.00
    ჸ
    -1.00
     ${({
    -1.00
    Specifica
    -1.00
     dzięki
    -0.99
    Invit
    -0.97
     []:
    -0.94
    jesz
    -0.94
    POSITIVE LOGITS
     only
    2.00
     said
    1.41
    only
    1.34
     says
    1.13
     cordes
    1.07
     ندارد
    1.07
    ONLY
    1.06
     showing
    1.05
    𝐁
    1.04
    ったのは
    1.03
    Activations Density 0.117%

    No Known Activations