© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39322
    Prev
    Next
    INDEX
    Explanations

    measuring approximately, showed much, had significantly

    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
     which
    -1.86
     also
    -1.66
     not
    -1.51
     or
    -1.48
     now
    -1.45
     will
    -1.43
    sendRedirect
    -1.21
     including
    -1.16
     from
    -1.14
    itteet
    -1.11
    POSITIVE LOGITS
    給你
    1.30
    ""}
    1.27
    however
    1.25
    considering
    1.23
    給我
    1.23
    ginal
    1.23
     eerst
    1.22
    presumably
    1.21
    chemia
    1.19
     Ս
    1.19
    Activations Density 0.203%

    No Known Activations