© 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. 100422
    Prev
    Next
    INDEX
    Explanations

    way, method, form, means

    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
    荦
    -2.73
     parachoque
    -2.52
    後記
    -2.45
     redaktion
    -2.39
    🪬
    -2.31
    茕
    -2.25
    鲩
    -2.25
    痾
    -2.25
     motocicletas
    -2.23
     enamorado
    -2.23
    POSITIVE LOGITS
    m
    2.63
    as
    2.63
    q
    2.36
     selben
    2.34
    v
    2.27
    j
    2.25
    l
    2.23
    ah
    2.17
     he
    2.16
     '
    2.13
    Activations Density 0.004%

    No Known Activations