© 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. 106759
    Prev
    Next
    INDEX
    Explanations

    the ... not the

    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
     možná
    -1.07
    llllllll
    -0.98
     basically
    -0.98
     неболь
    -0.92
    }\}$
    -0.92
    basically
    -0.91
     nejen
    -0.89
     málo
    -0.89
    dopodob
    -0.89
     both
    -0.88
    POSITIVE LOGITS
     sondern
    1.54
     anymore
    1.48
     same
    1.34
     nor
    1.30
     usual
    1.29
    而是
    1.27
     necessarily
    1.19
     slightest
    1.17
     type
    1.14
     אלא
    1.12
    Activations Density 0.026%

    No Known Activations