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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 446
    Prev
    Next
    INDEX
    Explanations

    programming syntax and keywords

    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_40_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
     ۳
    0.49
     ૩
    0.46
    ३
    0.42
    <0xBB>
    0.42
    𝟑
    0.39
     treinta
    0.37
    creates
    0.37
    ۳
    0.37
    ૩
    0.37
     পদার্থ
    0.36
    POSITIVE LOGITS
     nové
    0.39
    éfonos
    0.38
    Бы
    0.38
     typer
    0.37
    〆
    0.36
     병
    0.35
     rez
    0.35
     UNC
    0.35
     Unix
    0.34
     Felix
    0.34
    Activations Density 0.004%

    No Known Activations