© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 858
    Prev
    Next
    INDEX
    Explanations

    And or okay introducing a phrase

    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
    าย
    1.26
     >=
    1.24
    內的
    1.21
     ?>
    1.19
    oelectric
    1.19
    <=
    1.14
     已
    1.11
    ﺀ
    1.10
    TREE
    1.09
    ならラクマ
    1.09
    POSITIVE LOGITS
     enquanto
    1.43
    доль
    1.41
     informações
    1.35
     justru
    1.34
     wszel
    1.33
     lorsqu
    1.32
     affrontare
    1.32
     například
    1.31
     ketika
    1.31
     ataques
    1.31
    Activations Density 0.832%

    No Known Activations