© 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. 65150
    Prev
    Next
    INDEX
    Explanations

    director or starring actor

    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
     permite
    -1.40
     permiti
    -1.33
     requiere
    -1.24
     offre
    -1.23
     umożliwia
    -1.23
     hace
    -1.22
    (!$
    -1.17
     tallas
    -1.16
    SqlParameter
    -1.16
     services
    -1.12
    POSITIVE LOGITS
     rodrigo
    1.17
     alberto
    1.15
     egenskaper
    1.10
    を
    1.09
    もしろ
    1.09
     nicolas
    1.05
     giorgio
    1.04
    האם
    1.03
    毕竟
    0.98
     fays
    0.98
    Activations Density 0.026%

    No Known Activations