© 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. 10-GEMMASCOPE-RES-131K
    7. 70852
    Prev
    Next
    INDEX
    Explanations

    quantities, locations, and descriptions

    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
     for
    -1.41
     to
    -1.40
    ಱ
    -1.23
    nit
    -1.16
     ondu
    -1.15
    тической
    -1.13
    "")
    -1.10
     evidente
    -1.09
     not
    -1.07
    慫
    -1.06
    POSITIVE LOGITS
     their
    1.75
     tomaron
    1.47
    彼らの
    1.46
    Most
    1.42
     tenían
    1.41
     nuestras
    1.41
    There
    1.34
     때문
    1.33
    They
    1.32
    Also
    1.32
    Activations Density 0.247%

    No Known Activations