© 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. 103547
    Prev
    Next
    INDEX
    Explanations

    specific items and details

    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
     on
    -1.21
     at
    -1.16
     or
    -1.13
     with
    -1.11
     as
    -1.00
     from
    -0.90
    läg
    -0.87
     without
    -0.87
    !!!!!
    -0.85
     during
    -0.84
    POSITIVE LOGITS
     reiterated
    1.02
     nonchal
    1.00
     lorsque
    0.99
    eight
    0.98
     goofy
    0.96
     joyful
    0.95
    nine
    0.94
     casamento
    0.92
     Quando
    0.91
    seven
    0.91
    Activations Density 0.000%

    No Known Activations