© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34051
    Prev
    Next
    INDEX
    Explanations

    biological, medical, or system concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    nouns related to professional or scientific concepts followed by commas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     that
    -1.55
     those
    -1.38
     these
    -1.38
     this
    -1.32
     not
    -1.27
     having
    -1.27
    :
    -1.24
     being
    -1.22
     very
    -1.20
     such
    -1.19
    POSITIVE LOGITS
     and
    2.78
    并且
    1.27
     และ
    1.26
    beur
    1.23
    ceedings
    1.19
    そして
    1.14
    并将
    1.09
     الاخ
    1.09
     quatre
    1.07
     그리고
    1.06
    Activations Density 0.065%

    No Known Activations