© 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. 30564
    Prev
    Next
    INDEX
    Explanations

    coming soon

    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
     verwacht
    -1.05
     kilku
    -0.96
     vrouw
    -0.94
     buono
    -0.94
     Rezept
    -0.94
     apsau
    -0.93
     Під
    -0.93
     mūsų
    -0.93
     podró
    -0.93
     sicura
    -0.93
    POSITIVE LOGITS
    izing
    1.30
     Turing
    1.30
    zing
    1.30
     ating
    1.29
     doping
    1.27
    ING
    1.25
    asing
    1.23
     Schilling
    1.23
    oring
    1.20
    ning
    1.18
    Activations Density 0.188%

    No Known Activations