© 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. 60644
    Prev
    Next
    INDEX
    Explanations

    given the context

    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
     you
    -1.30
     nawr
    -1.13
     fometimes
    -1.11
     like
    -1.07
     kapag
    -1.06
    inį
    -1.04
     ejemplo
    -1.04
    sometimes
    -0.99
     tij
    -0.97
    ignants
    -0.97
    POSITIVE LOGITS
     it
    2.41
     could
    1.96
     if
    1.91
     whether
    1.77
     were
    1.70
     was
    1.63
     Given
    1.61
     given
    1.60
     могли
    1.59
    Given
    1.55
    Activations Density 0.038%

    No Known Activations