© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99065
    Prev
    Next
    INDEX
    Explanations

    as being

    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
    もあった
    -1.28
     these
    -1.23
    可谓
    -1.17
    ciso
    -1.13
    時的
    -1.13
    這些
    -1.12
     hias
    -1.10
    しかも
    -1.10
     various
    -1.08
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.07
    POSITIVE LOGITS
     being
    4.16
     having
    3.55
     étant
    2.75
    having
    2.52
     sendo
    2.52
     ayant
    2.42
     a
    2.39
    being
    2.30
     needing
    2.13
     fiind
    2.08
    Activations Density 0.081%

    No Known Activations