© 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. 22-GEMMASCOPE-RES-131K
    7. 26555
    Prev
    Next
    INDEX
    Explanations

    quantitatively comparing findings

    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_22/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
     تقری
    -1.27
    usually
    -1.27
     meistens
    -1.24
    さまで
    -1.24
    茑
    -1.20
     格式
    -1.19
     genellikle
    -1.19
     geralmente
    -1.18
     fleuve
    -1.14
    Ⴀ
    -1.14
    POSITIVE LOGITS
     and
    1.95
     or
    1.54
     other
    1.53
     different
    1.40
     maybe
    1.30
     specific
    1.26
     misschien
    1.25
     vielleicht
    1.24
     truly
    1.22
     especially
    1.21
    Activations Density 0.037%

    No Known Activations