© 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. 1494
    Prev
    Next
    INDEX
    Explanations

    parole, parody

    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
     —
    -3.44
     \
    -2.84
    Zubereitung
    -2.55
    ஂ
    -2.41
     \&
    -2.38
    又は
    -2.27
    狀況
    -2.14
    end
    -2.13
    1
    -2.13
    in
    -2.11
    POSITIVE LOGITS
    e
    2.56
    ruptcy
    2.48
    訫
    2.45
    鹚
    2.39
     .'
    2.38
    industan
    2.36
    abaikan
    2.23
     Estructura
    2.22
    isers
    2.17
    droje
    2.17
    Activations Density 0.002%

    No Known Activations