© 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. 22-GEMMASCOPE-RES-131K
    7. 34310
    Prev
    Next
    INDEX
    Explanations

    seeking explanatory context

    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
     when
    -1.34
    endurch
    -1.27
    nibus
    -1.13
    崩溃
    -1.05
     quando
    -1.02
    ialmente
    -1.02
    ་
    -1.00
     although
    -1.00
     if
    -1.00
     když
    -0.98
    POSITIVE LOGITS
     see
    1.47
    ,
    1.40
     please
    1.36
     more
    1.21
     более
    1.16
    ～、
    1.16
     purposes
    1.14
    Appellants
    1.11
     we
    1.10
     muualla
    1.09
    Activations Density 0.023%

    No Known Activations