© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83144
    Prev
    Next
    INDEX
    Explanations

    as below or follows

    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
    Roadmap
    -0.90
    أما
    -0.80
    dokument
    -0.80
    ?&
    -0.77
    ಂದು
    -0.76
    plakat
    -0.75
    fores
    -0.75
     그것
    -0.73
    Prologue
    -0.73
    Calculated
    -0.72
    POSITIVE LOGITS
     given
    4.66
    given
    3.42
    Given
    3.20
     mentioned
    2.86
     Given
    2.67
     GIVEN
    2.48
     gegeben
    2.09
     diberikan
    2.08
     dado
    1.91
     mention
    1.89
    Activations Density 0.069%

    No Known Activations