© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63951
    Prev
    Next
    INDEX
    Explanations

    getting things done

    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_34/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
     Konzer
    -0.88
    ӯ
    -0.86
    fährt
    -0.79
    @__
    -0.78
    jähriger
    -0.77
    lichte
    -0.77
     rins
    -0.76
     recherchez
    -0.75
    ễm
    -0.75
     کننده
    -0.75
    POSITIVE LOGITS
     done
    6.56
    done
    4.53
    Done
    4.19
     Done
    3.78
     DONE
    3.13
    DONE
    3.11
     dilakukan
    2.36
     accomplished
    2.33
     performed
    2.27
     gedaan
    2.22
    Activations Density 0.037%

    No Known Activations