© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27181
    Prev
    Next
    INDEX
    Explanations

    Proper names and identifiers

    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
    ----</
    -1.27
    粪
    -1.20
    GLenum
    -1.20
    ־ה
    -1.19
    わかる
    -1.18
    iffance
    -1.16
    ."</
    -1.16
     enunci
    -1.16
     ilustracji
    -1.16
    zinha
    -1.12
    POSITIVE LOGITS
     condenado
    1.30
     [''],
    1.28
    ↵↵↵
    1.21
     municipalité
    1.21
    |}\
    1.14
    Different
    1.13
    More
    1.13
    荭
    1.13
    
    1.13
     olabilir
    1.11
    Activations Density 0.019%

    No Known Activations