© 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. 34337
    Prev
    Next
    INDEX
    Explanations

    Thank you

    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
     illustre
    -1.55
     ..........
    -1.48
     kalender
    -1.44
     flotte
    -1.41
     ...........
    -1.38
     congrès
    -1.34
     politika
    -1.33
    露出了
    -1.30
     praktis
    -1.30
     menyen
    -1.28
    POSITIVE LOGITS
     More
    1.52
     Is
    1.49
     Have
    1.41
     Don
    1.27
     No
    1.26
     Has
    1.26
     Not
    1.25
     As
    1.24
     Many
    1.23
     Because
    1.23
    Activations Density 0.252%

    No Known Activations