© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14112
    Prev
    Next
    INDEX
    Explanations

    originating from Penang

    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
    𝖑
    2.43
     médiane
    2.36
    ुण
    2.32
    𝙜
    2.27
    zione
    2.21
    ̀
    2.20
     useRouter
    2.19
     kalo
    2.19
    ॉ
    2.14
    𝙥
    2.12
    POSITIVE LOGITS
    getCurrent
    2.59
    десят
    2.22
    theorem
    2.21
    трибу
    2.19
    틱
    2.18
    reduce
    2.15
    يع
    2.15
    TH
    2.14
    Abi
    2.12
    BLY
    2.12
    Activations Density 0.000%

    No Known Activations