© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79970
    Prev
    Next
    INDEX
    Explanations

    negation and limitation

    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
     folhas
    -1.24
    ᅫ
    -1.19
     pantalones
    -1.14
     voetballer
    -1.13
     salonu
    -1.10
    Ȝ
    -1.10
     botines
    -1.10
    værende
    -1.10
    nehmen
    -1.09
     guantes
    -1.09
    POSITIVE LOGITS
     because
    1.37
     are
    1.36
     through
    1.34
     is
    1.25
     to
    1.20
     they
    1.18
    At
    1.13
     have
    1.12
     were
    1.12
     from
    1.09
    Activations Density 0.040%

    No Known Activations