© 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. 65474
    Prev
    Next
    INDEX
    Explanations

    conditional probability given covariates

    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
    casus
    -0.75
    boi
    -0.70
    ertz
    -0.69
     RUD
    -0.68
     synonym
    -0.68
     Katie
    -0.67
    味付け
    -0.67
    alf
    -0.67
    bbl
    -0.67
     lounge
    -0.67
    POSITIVE LOGITS
     conditional
    4.94
    conditional
    4.50
    Conditional
    4.38
     Conditional
    4.22
     conditioned
    4.19
     conditioning
    3.73
    conditioned
    3.59
     Conditioning
    3.42
     conditionally
    3.16
    conditioning
    3.13
    Activations Density 0.098%

    No Known Activations