© 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. 15381
    Prev
    Next
    INDEX
    Explanations

    jeff followed by a name

    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
    er
    -2.52
    鉝
    -2.45
    乆
    -2.33
     детьми
    -2.31
     größeren
    -2.25
     speziellen
    -2.20
    this
    -2.20
     proficient
    -2.14
     ähnlichen
    -2.14
    投诉
    -2.11
    POSITIVE LOGITS
    ’
    3.34
    '
    2.27
    也
    2.25
    不会
    2.23
    VolleyError
    2.22
    赂
    2.19
    section
    2.17
    屙
    2.13
    的
    2.09
     Arabidopsis
    2.06
    Activations Density 0.034%

    No Known Activations