© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129844
    Prev
    Next
    INDEX
    Explanations

    code syntax and types

    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
    velocityX
    -1.43
     verrez
    -1.37
     „
    -1.32
     to
    -1.27
    wardship
    -1.22
     Palabra
    -1.20
    AfterViewInit
    -1.16
     can
    -1.15
     FontWeight
    -1.13
     ``
    -1.11
    POSITIVE LOGITS
     этих
    1.35
    There
    1.29
    ≦
    1.26
     also
    1.23
    每
    1.22
    Also
    1.20
    歳の
    1.13
    AGEM
    1.13
    يح
    1.11
    entendre
    1.11
    Activations Density 0.028%

    No Known Activations