© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14377
    Prev
    Next
    INDEX
    Explanations

    introducing quotes

    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
    s
    -2.94
    …”
    -2.47
    m
    -2.38
    f
    -2.33
    n
    -2.28
    ization
    -2.25
    ஂ
    -2.25
    IANGLES
    -2.23
        
    -2.22
    螅
    -2.22
    POSITIVE LOGITS
    UCIÓN
    2.39
    菹
    2.39
    ruguay
    2.31
    geſ
    2.30
     keramik
    2.27
     entregas
    2.25
    に応
    2.23
     OGSÅ
    2.22
    をしていた
    2.22
    passer
    2.20
    Activations Density 0.007%

    No Known Activations