© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98459
    Prev
    Next
    INDEX
    Explanations

    plural determiners and 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
     after
    -1.70
     that
    -1.63
     when
    -1.60
     and
    -1.57
     at
    -1.55
     with
    -1.44
     or
    -1.41
     during
    -1.32
     to
    -1.28
     for
    -1.27
    POSITIVE LOGITS
     respectively
    2.58
     båda
    2.53
     respective
    2.48
     begge
    2.42
     beiden
    2.42
     both
    2.42
     beide
    2.41
    respectively
    2.38
    それぞれ
    2.25
     оба
    2.25
    Activations Density 0.070%

    No Known Activations