© 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. 62965
    Prev
    Next
    INDEX
    Explanations

    likely to happen

    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
     sly
    -1.34
    alamualaikum
    -1.20
     uplifting
    -1.15
     eminently
    -1.13
    ","","
    -1.10
    比如说
    -1.08
     accelerating
    -1.07
     unwarranted
    -1.07
     ventes
    -1.05
     conquering
    -1.05
    POSITIVE LOGITS
     to
    2.88
    hood
    1.84
     be
    1.38
     candidates
    1.36
     gonna
    1.13
     suspects
    1.13
     outcome
    1.13
     scenario
    1.11
     izvē
    1.10
     antworte
    1.09
    Activations Density 0.014%

    No Known Activations