© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73145
    Prev
    Next
    INDEX
    Explanations

    manifest refraction

    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
     only
    -1.22
     или
    -1.07
     žena
    -1.06
    になりますが
    -1.03
     in
    -1.03
     фун
    -1.00
     or
    -1.00
     löst
    -0.96
     also
    -0.96
    coglie
    -0.96
    POSITIVE LOGITS
    iennes
    0.97
    **/
    0.94
     Evita
    0.91
    Varios
    0.91
     concret
    0.91
     ressemb
    0.91
     Consum
    0.91
     véhic
    0.91
    Estab
    0.88
     Toscana
    0.88
    Activations Density 0.003%

    No Known Activations