© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57644
    Prev
    Next
    INDEX
    Explanations

    addressing you

    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
    錞
    -2.14
     at
    -1.55
    ญี่ป
    -1.48
    chọn
    -1.43
     our
    -1.42
     наших
    -1.40
    厦门
    -1.35
     gancho
    -1.34
    Какой
    -1.34
    ﾐ
    -1.33
    POSITIVE LOGITS
    9
    1.57
     etc
    1.50
     protože
    1.45
     എന്ന
    1.43
     montrent
    1.38
     Bedürf
    1.37
    hese
    1.34
    borderSide
    1.33
    sw
    1.32
     perché
    1.32
    Activations Density 0.041%

    No Known Activations