© 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. 34-GEMMASCOPE-RES-131K
    7. 78044
    Prev
    Next
    INDEX
    Explanations

    URL separators and code syntax

    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_34/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
     not
    -1.38
     one
    -1.18
     Despite
    -1.17
     came
    -1.14
    ']==
    -1.06
     At
    -1.05
    '},
    -1.05
    ׀
    -1.03
     Although
    -1.03
     While
    -1.03
    POSITIVE LOGITS
    _
    2.55
    _-_
    1.76
    %
    1.59
     
    1.35
    ︐
    1.27
     poissons
    1.27
     diriger
    1.27
    \_
    1.25
    particularly
    1.23
    nbsp
    1.23
    Activations Density 0.092%

    No Known Activations