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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14198
    Prev
    Next
    INDEX
    Explanations

    Let's followed by an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    و
    0.88
    Д
    0.81
    ЛЕ
    0.79
     Heartland
    0.78
    ا
    0.77
    𝙈
    0.76
    2
    0.75
     consumables
    0.75
    ,
    0.75
    itlement
    0.73
    POSITIVE LOGITS
    ید
    1.18
    is
    1.09
    ла
    0.96
    deki
    0.88
    ана
    0.87
     başlayalım
    0.86
    ujourd
    0.86
    до
    0.83
    ına
    0.82
    то
    0.81
    Activations Density 0.090%

    No Known Activations