© 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. 10-GEMMASCOPE-RES-131K
    7. 84344
    Prev
    Next
    INDEX
    Explanations

    semi- automatic, synthetic, automatic

    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_10/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
     any
    -1.64
     T
    -1.64
     sowohl
    -1.52
    ↵
    -1.50
     In
    -1.47
     <
    -1.47
    To
    -1.44
     And
    -1.41
     To
    -1.37
     A
    -1.35
    POSITIVE LOGITS
     dekoratif
    1.49
     ――――――――
    1.46
     tabak
    1.45
     continuare
    1.41
     liberi
    1.40
    ╂
    1.40
    selbe
    1.36
     parfü
    1.34
     continuant
    1.34
     Selanjutnya
    1.33
    Activations Density 0.046%

    No Known Activations