© 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. 22-GEMMASCOPE-RES-131K
    7. 25557
    Prev
    Next
    INDEX
    Explanations

    identifier followed by assignment

    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
     its
    -1.56
     Když
    -1.29
     Além
    -1.28
     krás
    -1.27
     Pokud
    -1.26
     their
    -1.23
    tink
    -1.23
    corrhi
    -1.19
     Może
    -1.18
    nyata
    -1.16
    POSITIVE LOGITS
     =
    1.63
    は
    1.17
    それでも
    1.03
     tristesse
    1.03
     antonio
    1.00
     delhi
    0.99
     '%'
    0.98
    ulously
    0.98
     carlo
    0.98
    文學
    0.96
    Activations Density 0.010%

    No Known Activations