© 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. 128718
    Prev
    Next
    INDEX
    Explanations

    personal statements expressing belief or experience

    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
    ‪.
    -1.23
    時期
    -1.17
    —”
    -1.16
     pomocą
    -1.16
     Fällen
    -1.16
    pozorn
    -1.16
    tentu
    -1.13
    instein
    -1.13
     députés
    -1.13
     cedera
    -1.12
    POSITIVE LOGITS
    "
    1.50
    ,"
    1.43
    ."
    1.43
     [
    1.40
    </b>
    1.38
    </strong>
    1.35
    '
    1.28
    </i>
    1.27
    ,
    1.24
    はこんな感じ
    1.15
    Activations Density 0.068%

    No Known Activations