© 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. 34-GEMMASCOPE-RES-131K
    7. 117714
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by related concepts

    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_34/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
    凄く
    -1.55
    色々な
    -1.51
     begann
    -1.51
    おわりに
    -1.50
     criado
    -1.48
    色んな
    -1.47
     insanely
    -1.45
     betreffende
    -1.45
    綺麗な
    -1.44
    凄い
    -1.43
    POSITIVE LOGITS
     one
    1.80
     because
    1.74
     ones
    1.65
     when
    1.57
     Both
    1.41
     as
    1.37
     after
    1.34
     azulejos
    1.34
    ⤵
    1.29
     went
    1.28
    Activations Density 0.484%

    No Known Activations