© 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. 23866
    Prev
    Next
    INDEX
    Explanations

    as long as

    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
     باید
    -1.20
     should
    -1.12
     bahkan
    -1.09
    ("]");
    -1.09
    ationen
    -1.07
    should
    -1.05
     ought
    -1.04
     often
    -1.02
     debía
    -1.01
    Should
    -0.99
    POSITIVE LOGITS
     there
    1.96
     they
    1.79
     it
    1.70
     don
    1.58
     isn
    1.47
     doesn
    1.45
     you
    1.37
     keep
    1.36
     remain
    1.35
     stay
    1.30
    Activations Density 0.016%

    No Known Activations