© 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. 39593
    Prev
    Next
    INDEX
    Explanations

    metallicity or chemical element

    np_acts-logits-general · gemini-2.5-flash-lite

    special symbols, code elements, and technical notation like parentheses, brackets, and technical object names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     of
    -1.84
     also
    -1.59
    については
    -1.40
    ↵↵
    -1.34
     departement
    -1.32
     présentés
    -1.32
     shouldn
    -1.28
     palab
    -1.27
     cinquième
    -1.26
    也是
    -1.23
    POSITIVE LOGITS
    Perhaps
    1.48
     use
    1.30
     ``
    1.30
     nordrhein
    1.30
     \"
    1.30
     nuestro
    1.30
     jesteśmy
    1.28
     jemals
    1.24
    During
    1.23
    Usually
    1.22
    Activations Density 0.547%

    No Known Activations