© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19747
    Prev
    Next
    INDEX
    Explanations

    sniffing and snuffing

    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
    一些
    -2.70
    ي
    -2.56
    赈
    -2.34
     tetapi
    -2.28
    actéristi
    -2.22
    ?”
    -2.20
    同じ
    -2.17
    jenigen
    -2.17
    鼩
    -2.14
    :</
    -2.13
    POSITIVE LOGITS
     comprennent
    2.11
     \%$.
    2.06
    Kenapa
    2.05
    鶿
    2.05
     donnent
    2.02
     techniczne
    2.02
    Hanya
    1.99
    ’
    1.98
    鴬
    1.97
     deviennent
    1.96
    Activations Density 0.005%

    No Known Activations