© 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. 10-GEMMASCOPE-RES-131K
    7. 73806
    Prev
    Next
    INDEX
    Explanations

    friend of mine

    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
     you
    -2.75
    しましたが
    -1.88
    ężczy
    -1.79
    扩张
    -1.77
    zegovina
    -1.76
    ophageal
    -1.71
     ruthless
    -1.69
    钒
    -1.64
    几种
    -1.64
    StateToProps
    -1.63
    POSITIVE LOGITS
     own
    2.27
    h
    2.14
    “
    2.11
    c
    2.05
    4
    2.00
    :
    1.98
    "
    1.94
    0
    1.90
    u
    1.88
    -“
    1.78
    Activations Density 0.004%

    No Known Activations