© 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. 11858
    Prev
    Next
    INDEX
    Explanations

    success outcomes

    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
    翃
    -2.92
     famoso
    -2.52
     spearheaded
    -2.44
     soooo
    -2.39
     incredibly
    -2.38
     astounding
    -2.38
     fabulous
    -2.36
     renowned
    -2.34
     sooo
    -2.30
     terrific
    -2.28
    POSITIVE LOGITS
    0
    3.14
    This
    2.98
    If
    2.92
    7
    2.83
    Also
    2.83
    With
    2.78
    That
    2.72
    Because
    2.67
    Despite
    2.61
    There
    2.56
    Activations Density 0.005%

    No Known Activations