© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40014
    Prev
    Next
    INDEX
    Explanations

    your positive choice

    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
    וּ
    -1.32
    וּ
    -1.30
    ּוֹ
    -1.24
     other
    -1.23
     libur
    -1.20
    Quiénes
    -1.18
    Cuándo
    -1.16
     вещей
    -1.16
    tainers
    -1.16
    asiswa
    -1.16
    POSITIVE LOGITS
     your
    2.50
     you
    2.30
    ׇ
    1.75
     our
    1.45
     YOU
    1.33
     שלנו
    1.33
    !
    1.24
     μας
    1.21
     TAMBIÉN
    1.20
    Your
    1.20
    Activations Density 0.042%

    No Known Activations