© 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. 64061
    Prev
    Next
    INDEX
    Explanations

    dates and ordinals

    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
     and
    -1.69
     like
    -1.49
     also
    -1.44
     not
    -1.38
     such
    -1.30
    ↵
    -1.27
     no
    -1.27
    /*
    -1.20
     for
    -1.18
     mostly
    -1.17
    POSITIVE LOGITS
     diriger
    1.55
     refroid
    1.48
     siè
    1.36
     favoriser
    1.30
     régal
    1.30
     rafra
    1.30
     remé
    1.29
    ,
    1.29
     recev
    1.28
     lutter
    1.28
    Activations Density 0.144%

    No Known Activations