© 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. 48599
    Prev
    Next
    INDEX
    Explanations

    SVG path data

    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
     with
    -1.40
     many
    -1.39
     several
    -1.35
     capable
    -1.27
     while
    -1.26
     small
    -1.23
     substantially
    -1.21
     considerable
    -1.20
     so
    -1.18
     large
    -1.17
    POSITIVE LOGITS
     ainda
    1.20
     ALREADY
    1.10
     blessures
    1.06
    verzeichnis
    1.00
    どっち
    1.00
    denied
    0.99
     incont
    0.98
    verhält
    0.98
    loves
    0.98
     imme
    0.97
    Activations Density 0.015%

    No Known Activations