© 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. 71820
    Prev
    Next
    INDEX
    Explanations

    I'm introductions

    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
     السياس
    -1.63
     الحكومة
    -1.41
    之事
    -1.24
    räder
    -1.23
    </table>
    -1.19
     правительства
    -1.19
    MILLISECONDS
    -1.17
     Kích
    -1.15
     jego
    -1.15
     矢量
    -1.15
    POSITIVE LOGITS
     this
    1.55
    .
    1.37
    ــــــــ
    1.36
     such
    1.30
     my
    1.10
     подарки
    1.09
     I
    1.09
    It
    1.06
    是这样的
    1.03
    ↵
    1.02
    Activations Density 0.163%

    No Known Activations