© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70257
    Prev
    Next
    INDEX
    Explanations

    green tip ammunition ban

    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_10/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
    訁
    -2.08
    甗
    -1.97
    ?’
    -1.92
     Eigentü
    -1.82
     accumulate
    -1.78
     streamline
    -1.77
     ehemal
    -1.73
     Therefore
    -1.73
     accommodate
    -1.69
     Historically
    -1.69
    POSITIVE LOGITS
     of
    3.17
    0
    2.47
     can
    1.73
    、
    1.73
     он
    1.71
     и
    1.66
    ."
    1.65
     ї
    1.63
     \
    1.62
    нный
    1.59
    Activations Density 0.017%

    No Known Activations