© 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. 48742
    Prev
    Next
    INDEX
    Explanations

    lists types of things

    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
    €“
    -1.47
    €”
    -1.38
     garder
    -1.35
    wijl
    -1.33
    primarily
    -1.24
    
    -1.24
     incroyable
    -1.23
     incont
    -1.23
     fleurs
    -1.22
     vôtre
    -1.20
    POSITIVE LOGITS
     related
    1.63
     various
    1.60
     some
    1.54
     including
    1.51
     after
    1.49
     different
    1.40
     ordinary
    1.37
     large
    1.36
     high
    1.36
     more
    1.36
    Activations Density 0.257%

    No Known Activations