© 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. 254
    Prev
    Next
    INDEX
    Explanations

    technical/academic citations

    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
     évidemment
    -0.79
     bajos
    -0.78
     }}\
    -0.78
     jamais
    -0.77
    arked
    -0.75
    ;=
    -0.72
    हरू
    -0.72
    dedicated
    -0.71
     cal
    -0.70
     Fake
    -0.70
    POSITIVE LOGITS
     Abba
    0.83
    illez
    0.80
     ffs
    0.75
     %-
    0.75
     handout
    0.74
     Uru
    0.73
    سیون
    0.73
     🥺
    0.73
     boho
    0.72
     minum
    0.72
    Activations Density 0.035%

    No Known Activations