© 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. 107088
    Prev
    Next
    INDEX
    Explanations

    declarations after punctuation

    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
     as
    -1.79
     by
    -1.73
     just
    -1.49
     these
    -1.47
     when
    -1.47
     only
    -1.44
     all
    -1.42
     although
    -1.41
     at
    -1.41
     there
    -1.38
    POSITIVE LOGITS
     faciliter
    1.16
     alluring
    1.16
    fion
    1.16
    מיש
    1.15
     siè
    1.14
     tumultuous
    1.14
     kleding
    1.13
     détect
    1.13
     empêcher
    1.13
     MICHAEL
    1.13
    Activations Density 0.014%

    No Known Activations