© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14534
    Prev
    Next
    INDEX
    Explanations

    Super and 1st/21st

    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_7_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
    ский
    2.54
    訕
    2.41
    न्यूयॉर्क
    2.40
    اً
    2.38
    وق
    2.33
    lı
    2.27
    পাঁ
    2.25
    琅
    2.23
    ::_
    2.21
    ἡ
    2.21
    POSITIVE LOGITS
    া
    2.83
    oja
    2.71
     holding
    2.67
    eid
    2.51
    eaa
    2.46
    aura
    2.41
    e
    2.38
    eek
    2.37
    場合に
    2.34
    ateral
    2.33
    Activations Density 0.023%

    No Known Activations