© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14864
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be' or 'corresponds'

    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
     or
    -1.55
     and
    -1.37
     when
    -1.35
     which
    -1.15
     take
    -1.13
     will
    -1.11
     takes
    -1.09
    when
    -1.06
    zło
    -1.05
     took
    -1.04
    POSITIVE LOGITS
    actually
    1.53
    seems
    1.39
     largely
    1.33
     muñeco
    1.25
     szint
    1.25
    quickly
    1.21
     triko
    1.20
    indicate
    1.20
     Schicht
    1.20
     különböző
    1.18
    Activations Density 0.087%

    No Known Activations