© 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. 22-GEMMASCOPE-RES-131K
    7. 67250
    Prev
    Next
    INDEX
    Explanations

    public relations agencies

    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_22/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
    Despite
    -1.65
    After
    -1.59
    Following
    -1.53
    There
    -1.52
    Those
    -1.52
    Without
    -1.46
    If
    -1.45
     only
    -1.45
    Many
    -1.43
    Perhaps
    -1.42
    POSITIVE LOGITS
    riy
    1.41
    addCriterion
    1.38
     tutaj
    1.37
    holdet
    1.37
    İŞ
    1.36
    櫈
    1.35
     interessante
    1.30
    ITO
    1.30
    ПЕ
    1.29
     sánh
    1.27
    Activations Density 0.020%

    No Known Activations