© 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. 45279
    Prev
    Next
    INDEX
    Explanations

    mainly by

    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
     because
    -1.27
     Perhaps
    -1.18
     when
    -1.05
     increases
    -1.05
     after
    -1.04
     with
    -1.04
     one
    -1.03
    méno
    -1.03
     at
    -1.03
     as
    -1.03
    POSITIVE LOGITS
     mainly
    6.63
    mainly
    6.31
     mostly
    6.31
    mostly
    6.22
    Mostly
    5.69
     principalmente
    5.53
     predominantly
    5.47
    Mainly
    5.47
     primarily
    5.44
     principalement
    5.38
    Activations Density 0.666%

    No Known Activations