© 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. 30724
    Prev
    Next
    INDEX
    Explanations

    program run normally

    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
     télécommande
    -1.08
     curioso
    -1.07
    𝐟
    -1.04
     exteriores
    -1.02
     câbles
    -1.02
    ClassNotFound
    -1.01
     ensuing
    -0.98
    final
    -0.95
     ſe
    -0.94
    past
    -0.94
    POSITIVE LOGITS
     by
    1.35
     with
    1.32
     for
    1.23
     without
    1.09
     again
    1.09
     in
    1.08
     more
    1.08
     before
    1.08
     from
    1.07
     here
    1.05
    Activations Density 0.009%

    No Known Activations