© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1085
    Prev
    Next
    INDEX
    Explanations

    ' quotation and its following letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    5
    0.46
    8
    0.45
    9
    0.45
    6
    0.43
    ↵↵
    0.43
    3
    0.42
    7
    0.42
    4
    0.40
    1
    0.36
    ↵↵↵
    0.35
    POSITIVE LOGITS
    ت
    0.34
    崚
    0.34
    த்
    0.33
     upstream
    0.33
    可能
    0.33
    سازی
    0.33
    𝗶
    0.33
    -->'
    0.32
     具体
    0.32
     አመ
    0.31
    Activations Density 2.979%

    No Known Activations