© 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. 7083
    Prev
    Next
    INDEX
    Explanations

    anticipating specification after what

    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
    ₩
    -1.16
    icie
    -1.13
     endforeach
    -1.05
    鵙
    -1.04
     settembre
    -1.04
    xffffff
    -1.03
    loggen
    -1.02
    潜力
    -1.01
    signia
    -1.01
    ános
    -1.01
    POSITIVE LOGITS
     kind
    2.70
     sort
    2.33
     kinds
    2.22
     sorts
    1.84
     type
    1.73
     types
    1.72
     additional
    1.45
    sort
    1.44
     exactly
    1.38
     might
    1.34
    Activations Density 0.056%

    No Known Activations