© 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. 40217
    Prev
    Next
    INDEX
    Explanations

    and other things

    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
     it
    -1.31
     бампер
    -1.27
     and
    -1.24
     موبایل
    -1.24
    ırlar
    -1.23
    ּוֹ
    -1.20
    がありました
    -1.17
    ִּ
    -1.17
     آیفون
    -1.16
    荐
    -1.14
    POSITIVE LOGITS
     گیاه
    1.45
     lecker
    1.21
     насеља
    1.16
    announced
    1.15
     liksom
    1.10
     навіть
    1.09
    vamo
    1.08
    H
    1.08
     sogar
    1.08
     generous
    1.08
    Activations Density 0.030%

    No Known Activations