Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2971
    Prev
    Next
    INDEX
    Explanations

    situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     १९
    1.08
    E
    1.08
    '!
    1.06
     subsidy
    1.06
     sparse
    1.05
     ২১
    1.03
     rescuers
    1.01
     ১৫
    1.01
     с
    1.01
    ′
    1.01
    POSITIVE LOGITS
     bilgis
    1.13
     サマータイヤ
    1.12
     dinh
    1.09
     stej
    1.08
    waż
    1.05
     Thì
    1.05
    ưa
    1.05
     khái
    1.05
     continuité
    1.04
    okrat
    1.04
    Activations Density 0.101%

    No Known Activations