© 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. 22-GEMMASCOPE-RES-131K
    7. 38619
    Prev
    Next
    INDEX
    Explanations

    and followed by conjunctions or pronouns

    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_22/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
     antaranya
    -1.46
    …»
    -1.33
    ℉
    -1.31
    ;",
    -1.23
    /</
    -1.23
    licopter
    -1.20
    ".
    -1.20
    oooooooo
    -1.20
    farers
    -1.19
    felves
    -1.17
    POSITIVE LOGITS
     this
    1.89
     there
    1.87
     it
    1.82
     we
    1.65
     each
    1.64
     these
    1.38
     our
    1.34
     should
    1.32
     many
    1.30
     every
    1.24
    Activations Density 0.061%

    No Known Activations