© 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. 41997
    Prev
    Next
    INDEX
    Explanations

    armed robberies

    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
    饃
    -1.68
     kontinu
    -1.49
    仫
    -1.47
    dö
    -1.45
    usata
    -1.44
    hướng
    -1.44
    źródło
    -1.44
     exponer
    -1.44
    ﻢ
    -1.44
     stanov
    -1.41
    POSITIVE LOGITS
     that
    1.69
    d
    1.55
    f
    1.54
    ”
    1.54
     
    1.43
    b
    1.43
    9
    1.40
    8
    1.38
     ”
    1.34
    <strong>
    1.32
    Activations Density 0.374%

    No Known Activations