© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246221
    Prev
    Next
    INDEX
    Explanations

    states, countries, and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.50
    넹
    0.47
    adihi
    0.44
    incinnati
    0.42
     voltage
    0.42
     minimax
    0.42
    INEN
    0.42
    leni
    0.42
    үндө
    0.42
    ból
    0.41
    POSITIVE LOGITS
     протя
    0.49
     Έ
    0.47
     клиен
    0.47
    ッシュ
    0.46
    ା
    0.46
    ગવાન
    0.46
     прока
    0.45
     распростра
    0.45
     трёх
    0.45
    ﺃ
    0.45
    Activations Density 0.001%

    No Known Activations