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-16K
    4. 1258
    Prev
    Next
    INDEX
    Explanations

    few + [quantifiable or listable noun]

    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_16k_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
    ان
    2.03
    न
    1.90
    ই
    1.80
    на
    1.67
    к
    1.67
     furtherance
    1.59
    লা
    1.57
    и
    1.56
     khoảng
    1.52
    된
    1.52
    POSITIVE LOGITS
    EST
    1.85
     dozen
    1.85
    ור
    1.79
    ture
    1.74
    torrent
    1.72
    dozen
    1.64
    THING
    1.59
     hundred
    1.56
    sky
    1.55
    ഋ
    1.52
    Activations Density 0.087%

    No Known Activations