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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52832
    Prev
    Next
    INDEX
    Explanations

    words after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    Choosing
    0.97
    Read
    0.96
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.95
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
    Selecting
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
    Creating
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    อยาก
    0.92
    Diversity
    0.91
    POSITIVE LOGITS
     his
    1.23
     its
    1.17
     their
    1.16
     later
    1.12
     then
    1.08
     her
    1.02
     meanwhile
    1.02
     그의
    0.99
     other
    0.96
     её
    0.96
    Activations Density 0.000%

    No Known Activations