© 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. 99661
    Prev
    Next
    INDEX
    Explanations

    goals for

    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
     begyn
    -1.47
     hias
    -1.45
     некоторы
    -1.45
     begy
    -1.41
     carlo
    -1.38
    onnaise
    -1.34
     sez
    -1.32
    =“
    -1.31
    -:
    -1.31
    <bos>
    -1.31
    POSITIVE LOGITS
     through
    1.60
     for
    1.44
     or
    1.37
     is
    1.34
     while
    1.33
    ﾍ
    1.32
     thru
    1.30
     with
    1.26
     would
    1.24
    wertes
    1.23
    Activations Density 1.091%

    No Known Activations