© 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. 49873
    Prev
    Next
    INDEX
    Explanations

    record label

    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
    alva
    -0.75
     Motorsport
    -0.69
     rám
    -0.68
     }?>
    -0.68
     выясни
    -0.66
     träd
    -0.66
     اشاره
    -0.66
    bfd
    -0.66
     villages
    -0.66
    kew
    -0.66
    POSITIVE LOGITS
     label
    5.03
    label
    4.63
     labels
    4.16
     Label
    3.53
    Label
    3.44
    LABEL
    3.22
    labels
    3.16
    Labels
    3.03
     Labels
    3.02
     LABEL
    2.95
    Activations Density 0.070%

    No Known Activations