© 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. 81194
    Prev
    Next
    INDEX
    Explanations

    as well

    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
    çon
    -0.87
    iran
    -0.84
     groter
    -0.77
    𝕓
    -0.76
    九月
    -0.76
    ীব
    -0.75
     particularmente
    -0.75
     maría
    -0.72
     automaticamente
    -0.72
    raga
    -0.71
    POSITIVE LOGITS
     well
    3.73
    Well
    2.39
     Well
    2.05
    well
    2.00
     WELL
    1.83
     hyvin
    1.73
     dobrze
    1.70
     as
    1.59
     jól
    1.55
     wells
    1.55
    Activations Density 0.012%

    No Known Activations