© 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. 15402
    Prev
    Next
    INDEX
    Explanations

    words beginning with "inter"

    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
     
    -3.81
     technisch
    -2.86
     Mehrheit
    -2.58
    ”？
    -2.58
    姽
    -2.55
     haupts
    -2.53
    有可能
    -2.50
     echte
    -2.48
     vanguardia
    -2.42
    難しい
    -2.34
    POSITIVE LOGITS
    珦
    3.08
    ⎆
    2.88
    ).
    2.88
    霂
    2.77
     That
    2.72
     $^{\
    2.69
    鸫
    2.66
     Not
    2.59
     What
    2.59
     Following
    2.58
    Activations Density 0.035%

    No Known Activations