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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3807
    Prev
    Next
    INDEX
    Explanations

    stirring with qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ea
    1.49
    i
    1.36
    ↵
    1.34
    zelfde
    1.33
    eau
    1.32
    ir
    1.31
    id
    1.27
    element
    1.27
    eous
    1.26
    ל
    1.26
    POSITIVE LOGITS
    s
    1.43
    Დ
    1.42
    𝙱
    1.41
    thed
    1.34
     arou
    1.32
     codons
    1.32
     fanfare
    1.30
    stens
    1.28
     redundancies
    1.27
    Მ
    1.27
    Activations Density 0.002%

    No Known Activations