© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112328
    Prev
    Next
    INDEX
    Explanations

    right now

    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_10/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
     of
    -3.55
     and
    -2.20
     \
    -2.11
     for
    -2.11
     to
    -2.09
    </strong>
    -1.92
     not
    -1.84
     or
    -1.77
     (
    -1.77
    </h1>
    -1.74
    POSITIVE LOGITS
     anunció
    2.30
    笵
    2.22
     revelou
    2.19
     éviter
    2.14
    
    2.08
     spezi
    2.06
    蘧
    2.05
    聽到
    2.05
    䜣
    2.03
    Doesn
    2.02
    Activations Density 0.008%

    No Known Activations