© 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. 119726
    Prev
    Next
    INDEX
    Explanations

    im followed by common phrases

    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
    C
    -3.20
     jährlich
    -2.64
     ausschließlich
    -2.64
    L
    -2.61
    تیجه
    -2.61
     mehrm
    -2.56
     beinahe
    -2.52
    Doesn
    -2.48
     incl
    -2.44
     детям
    -2.44
    POSITIVE LOGITS
     was
    2.84
     hebben
    2.72
    翃
    2.69
    rierten
    2.38
    螻
    2.36
    יצוני
    2.33
    馓
    2.33
    猻
    2.33
    ⢌
    2.31
    
    2.30
    Activations Density 0.009%

    No Known Activations