© 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. 30412
    Prev
    Next
    INDEX
    Explanations

    intended for

    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
     it
    -0.99
    日は
    -0.95
    wnie
    -0.91
    ciety
    -0.90
     obo
    -0.90
    opedia
    -0.90
     моей
    -0.89
    vereignty
    -0.88
    morphosis
    -0.88
    mtb
    -0.88
    POSITIVE LOGITS
     those
    1.80
    Those
    1.43
     if
    1.31
     you
    1.25
    大家
    1.20
    那些
    1.13
     Those
    1.09
     ancora
    1.07
     when
    1.06
    当你
    1.06
    Activations Density 0.021%

    No Known Activations