© 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. 22-GEMMASCOPE-RES-131K
    7. 130943
    Prev
    Next
    INDEX
    Explanations

    Enrique Serrano

    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_22/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
     blusa
    -1.39
     hacían
    -1.31
     ۱۸
    -1.20
    LEBR
    -1.17
     everyone
    -1.13
     dapatkan
    -1.09
     afbeelding
    -1.07
     berdua
    -1.07
     pulsera
    -1.06
     devez
    -1.05
    POSITIVE LOGITS
    AT
    1.09
     modestly
    1.09
    IS
    1.04
    خرى
    1.04
    ické
    1.03
    里面的
    1.02
    aa
    1.02
     predominant
    1.01
    lesssim
    1.00
     M
    0.99
    Activations Density 0.000%

    No Known Activations