© 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. 3914
    Prev
    Next
    INDEX
    Explanations

    your followed by a noun

    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
    Sú
    -1.41
     even
    -1.39
     oportunidades
    -1.34
     venía
    -1.34
    These
    -1.31
    ’，
    -1.31
     vivía
    -1.30
    carteles
    -1.30
     sensaciones
    -1.29
     tentar
    -1.27
    POSITIVE LOGITS
    mantec
    1.45
    揍
    1.42
     of
    1.41
     them
    1.29
     siehe
    1.22
     and
    1.21
     employee
    1.20
    celes
    1.19
     centaines
    1.19
     funeral
    1.18
    Activations Density 0.201%

    No Known Activations