© 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. 9515
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    それを
    -1.09
    ↵↵
    -1.07
    を
    -1.06
    但却
    -1.03
    同様に
    -1.03
     christlichen
    -1.01
     was
    -1.01
    ()
    -1.00
    場所は
    -1.00
     also
    -0.98
    POSITIVE LOGITS
    さぁ
    1.16
    Klima
    1.14
     keker
    1.13
     zelve
    1.11
     renon
    1.11
    instructor
    1.10
     kabát
    1.10
     cantar
    1.09
     intérêts
    1.09
    Kuva
    1.09
    Activations Density 0.065%

    No Known Activations