© 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. 10-GEMMASCOPE-RES-131K
    7. 41060
    Prev
    Next
    INDEX
    Explanations

    early hoursfinal minutes

    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
    ">${
    -1.80
    鱚
    -1.75
     ausgestattet
    -1.72
    😐
    -1.68
    ٳ
    -1.66
     westfalen
    -1.66
     最強
    -1.66
    葑
    -1.65
    彼女は
    -1.65
    優れた
    -1.63
    POSITIVE LOGITS
     This
    2.05
    This
    1.95
    d
    1.80
     We
    1.72
    l
    1.72
     unsere
    1.70
     их
    1.65
     of
    1.61
    le
    1.58
    for
    1.57
    Activations Density 0.004%

    No Known Activations