© 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. 90469
    Prev
    Next
    INDEX
    Explanations

    struggle against

    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
     pierwszym
    -1.55
    废话
    -1.52
     new
    -1.49
    bảng
    -1.48
    店長
    -1.48
    来自于
    -1.48
     armados
    -1.48
    二日
    -1.44
     enfermos
    -1.44
    phòng
    -1.44
    POSITIVE LOGITS
    已然
    1.53
     وإ
    1.41
    </u>
    1.41
    ти
    1.37
    RAINE
    1.37
     beziehungs
    1.36
     помогают
    1.35
    簓
    1.33
     against
    1.31
     harass
    1.31
    Activations Density 0.028%

    No Known Activations