© 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. 66102
    Prev
    Next
    INDEX
    Explanations

    reporting speech or claims

    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
     lintas
    -1.12
     ungefär
    -1.04
     примерно
    -1.04
    věr
    -1.03
     själva
    -1.02
     endast
    -1.02
     acudi
    -1.02
     What
    -0.96
    psfrag
    -0.94
    到这里
    -0.94
    POSITIVE LOGITS
     his
    1.69
     himself
    1.64
     erfolgre
    1.09
    濕
    1.05
     zufried
    1.03
    ἀ
    1.02
     daughter
    1.02
    ences
    1.00
    ських
    1.00
    Articulo
    0.99
    Activations Density 0.037%

    No Known Activations