© 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. 45574
    Prev
    Next
    INDEX
    Explanations

    primer and coatings

    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
     Estructura
    -0.75
     énon
    -0.73
    Referencias
    -0.71
     zahrani
    -0.70
    ENER
    -0.69
    вании
    -0.69
    OURI
    -0.69
     Fazit
    -0.69
     ¡¡
    -0.69
    gemeinde
    -0.68
    POSITIVE LOGITS
     primer
    2.56
     priming
    2.25
     primers
    2.23
     prime
    2.17
     primes
    2.06
     Prime
    2.00
     primed
    1.97
     Primer
    1.92
    Prime
    1.87
    PRIME
    1.78
    Activations Density 0.053%

    No Known Activations