© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 80004
    Prev
    Next
    INDEX
    Explanations

    introducing a concession

    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
     and
    -2.27
     or
    -1.76
    极为
    -1.70
     {
    -1.59
     APPELLATE
    -1.55
    ⚢
    -1.47
     semua
    -1.47
    förmig
    -1.46
    籐
    -1.45
     activiteiten
    -1.43
    POSITIVE LOGITS
    while
    2.19
    We
    2.08
    They
    1.95
    However
    1.91
     a
    1.88
    The
    1.86
    These
    1.85
    there
    1.81
    including
    1.80
    This
    1.75
    Activations Density 0.006%

    No Known Activations