© 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. 40271
    Prev
    Next
    INDEX
    Explanations

    me too / i do

    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
     celana
    -1.58
     proposito
    -1.42
    ⸫
    -1.41
     كيفية
    -1.41
     sarung
    -1.38
     kullanılan
    -1.36
     kald
    -1.34
    〜。
    -1.34
     part
    -1.31
     miten
    -1.31
    POSITIVE LOGITS
    ༼
    1.34
    diging
    1.33
     then
    1.26
    给他们
    1.18
    京都
    1.18
    también
    1.17
     superiori
    1.17
    .",
    1.16
    achet
    1.16
    Inicio
    1.16
    Activations Density 0.015%

    No Known Activations