© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31916
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     as
    -1.41
     diminish
    -1.20
     three
    -1.19
     all
    -1.16
     two
    -1.16
     at
    -1.11
     through
    -1.09
     four
    -1.09
     without
    -1.09
     from
    -1.06
    POSITIVE LOGITS
    。
    1.41
    OUR
    1.38
    .”
    1.35
    ğın
    1.33
    ，
    1.32
    omato
    1.28
    €“
    1.27
     overarching
    1.27
    oftware
    1.24
     også
    1.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.