© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67130
    Prev
    Next
    INDEX
    Explanations

    DV prefix or acronym

    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
    ...”
    -2.42
    
    -2.34
    ”;
    -2.31
     When
    -2.27
     Hence
    -2.23
     resembling
    -2.22
    ếc
    -2.17
     "")
    -2.16
     """
    -2.14
     However
    -2.13
    POSITIVE LOGITS
    and
    2.98
    ーーーー
    2.27
    ERS
    2.08
    看你
    2.03
     rests
    1.96
     "
    1.91
    you
    1.90
    讓你
    1.88
     biggest
    1.86
    になり
    1.86
    Activations Density 0.005%

    No Known Activations