© 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. 34-GEMMASCOPE-RES-131K
    7. 83965
    Prev
    Next
    INDEX
    Explanations

    numbers and intensifiers

    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
     with
    -1.57
     because
    -1.51
     during
    -1.50
     which
    -1.44
     when
    -1.41
     including
    -1.41
     that
    -1.37
     from
    -1.32
     Since
    -1.31
     every
    -1.30
    POSITIVE LOGITS
     trois
    1.33
     unbelievably
    1.25
     insanely
    1.25
     sooo
    1.22
     soooo
    1.21
    six
    1.20
     cinq
    1.19
     pivotal
    1.19
     ridiculously
    1.19
     cuatro
    1.18
    Activations Density 0.000%

    No Known Activations