© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21515
    Prev
    Next
    INDEX
    Explanations

    the word says

    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
    ꪔ
    -2.69
    )$
    -2.55
    鉝
    -2.47
    ⑊
    -2.45
     have
    -2.38
    饺子
    -2.36
    ⢅
    -2.34
     декабря
    -2.33
    ቬ
    -2.31
    试图
    -2.30
    POSITIVE LOGITS
    es
    2.34
     says
    2.25
    фов
    2.13
     However
    2.11
    In
    2.05
     —
    2.03
    わか
    2.02
    ות
    2.00
     
    1.98
     Then
    1.95
    Activations Density 0.011%

    No Known Activations