© 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. 63208
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
     While
    -2.05
     Despite
    -2.03
     Although
    -1.91
     Regardless
    -1.90
     However
    -1.88
     Usually
    -1.84
     Even
    -1.68
     Generally
    -1.66
     despite
    -1.64
     Before
    -1.63
    POSITIVE LOGITS
     descuentos
    1.57
     vijf
    1.55
     คา
    1.53
     komplet
    1.52
     hermosos
    1.51
     myriad
    1.50
     wonderfully
    1.48
     autén
    1.45
     principalement
    1.45
     puramente
    1.45
    Activations Density 0.092%

    No Known Activations