© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 74998
    Prev
    Next
    INDEX
    Explanations

    </ followed by code constructs

    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_22/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
     fotógrafo
    -1.32
    арт
    -1.23
    haviours
    -1.22
     regardé
    -1.21
    ของ
    -1.21
    ไม่
    -1.21
    luka
    -1.21
    yeah
    -1.20
     estudiante
    -1.20
    เรา
    -1.18
    POSITIVE LOGITS
     length
    1.29
     there
    1.23
    _
    1.17
    k
    1.11
     size
    1.10
     number
    1.08
     первом
    1.06
    始まる
    1.04
    c
    1.02
     each
    1.01
    Activations Density 0.009%

    No Known Activations