© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59688
    Prev
    Next
    INDEX
    Explanations

    list delimiters, code syntax

    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
     has
    -1.43
    ,
    -1.41
     is
    -1.35
     and
    -1.34
    ऋ
    -1.27
     parati
    -1.25
     following
    -1.23
    　　《
    -1.22
    講演
    -1.20
    綑
    -1.20
    POSITIVE LOGITS
     davvero
    1.44
     extraña
    1.41
     THEIR
    1.40
     recev
    1.36
     délib
    1.35
     wirklich
    1.35
     abenço
    1.35
    ärin
    1.34
     русской
    1.33
     comiendo
    1.33
    Activations Density 0.048%

    No Known Activations