© 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. 10-GEMMASCOPE-RES-131K
    7. 86179
    Prev
    Next
    INDEX
    Explanations

    kindergarten and preschool

    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
    栳
    -3.38
    en
    -2.50
    ti
    -2.45
     steeped
    -2.39
    ’;
    -2.31
    vin
    -2.30
     quando
    -2.23
     vše
    -2.20
    龶
    -2.19
    甃
    -2.16
    POSITIVE LOGITS
    .
    2.50
    姈
    2.48
    靣
    2.36
    ྅
    2.33
    桧
    2.22
     schnellen
    2.05
    ₶
    2.03
     ontwikkel
    2.03
     raison
    2.02
    驀
    1.98
    Activations Density 0.003%

    No Known Activations