© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34626
    Prev
    Next
    INDEX
    Explanations

    actionbar, navigation bar, MenuBar

    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
     définiti
    -1.40
    bedrijf
    -1.31
     from
    -1.27
    分で
    -1.27
     bolí
    -1.26
    分に
    -1.25
     maneiras
    -1.24
     like
    -1.23
     стоковые
    -1.20
     Privacidade
    -1.17
    POSITIVE LOGITS
    <bos>
    1.55
    は
    1.27
    がありますが
    1.27
    ↵
    1.26
    など
    1.23
     is
    1.22
    と
    1.20
    によって
    1.16
    成员
    1.12
     новой
    1.11
    Activations Density 0.000%

    No Known Activations