© 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. 22-GEMMASCOPE-RES-131K
    7. 98650
    Prev
    Next
    INDEX
    Explanations

    punctuation around keywords

    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
     rése
    -1.28
     pán
    -1.23
    明日は
    -1.22
     histoires
    -1.20
     Mores
    -1.20
    declared
    -1.20
    総評
    -1.19
     helpt
    -1.18
    メルカリ
    -1.18
    Luxem
    -1.16
    POSITIVE LOGITS
     also
    1.36
     M
    1.18
     to
    1.16
    b
    1.16
     W
    1.15
    r
    1.14
    z
    1.13
    f
    1.13
     J
    1.12
    j
    1.12
    Activations Density 0.064%

    No Known Activations