© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1623
    Prev
    Next
    INDEX
    Explanations

    of course, of all, of interest

    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
     before
    -1.14
     and
    -1.11
     after
    -1.05
     by
    -1.05
     in
    -1.02
     as
    -1.00
     both
    -1.00
     it
    -0.99
     during
    -0.98
     on
    -0.96
    POSITIVE LOGITS
     the
    1.48
    Of
    1.33
     naturellement
    1.24
    naturally
    1.17
     all
    1.16
     všet
    1.13
    Naturally
    1.12
     interessant
    1.12
     note
    1.09
    perhaps
    1.09
    Activations Density 0.019%

    No Known Activations