© 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. 77808
    Prev
    Next
    INDEX
    Explanations

    so adjective that

    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
     quite
    -1.45
     or
    -1.34
     khá
    -1.30
     very
    -1.29
     rather
    -1.24
     enough
    -1.19
     ebenfalls
    -1.05
    かどうか
    -1.05
    得出
    -0.97
     molto
    -0.95
    POSITIVE LOGITS
     that
    4.91
     it
    2.94
     you
    1.97
     že
    1.68
     که
    1.65
     înc
    1.60
     που
    1.51
    それが
    1.51
     they
    1.45
     sehingga
    1.41
    Activations Density 0.026%

    No Known Activations