© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130500
    Prev
    Next
    INDEX
    Explanations

    locations and geographical entities

    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
     Erkrank
    -1.13
    }},\
    -1.02
    ;*/
    -1.01
     abzu
    -0.99
    他不
    -0.99
     stöd
    -0.99
     bleib
    -0.99
     одну
    -0.99
     Stoffe
    -0.98
    他也
    -0.97
    POSITIVE LOGITS
     where
    1.41
    Даже
    1.21
    Especially
    1.08
     όπου
    1.02
    Składniki
    1.01
    Where
    1.00
    Наши
    0.97
    Где
    0.97
    Mesmo
    0.94
    With
    0.94
    Activations Density 0.037%

    No Known Activations