© 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. 95
    Prev
    Next
    INDEX
    Explanations

    data table, C#, SQL

    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
    6
    -1.39
     (
    -1.37
     and
    -1.16
    3
    -1.15
     on
    -1.13
    7
    -1.10
    8
    -1.05
    憐
    -1.05
     a
    -1.02
    9
    -1.02
    POSITIVE LOGITS
    ּוֹ
    1.48
    ̴
    1.27
     posteriormente
    1.24
    ífico
    1.20
    Istanbul
    1.19
    </table>
    1.14
    egd
    1.13
    ִּ
    1.11
     rivière
    1.11
    וֹ
    1.09
    Activations Density 0.006%

    No Known Activations