© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1568
    Prev
    Next
    INDEX
    Explanations

    compound nouns ending in ity, ry, or ture

    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
    ם
    2.41
    ங்கிணை
    2.36
    이나
    2.28
    ம்
    2.19
    ില്‍
    2.06
    يه
    2.02
    ীয়
    2.00
     связанных
    1.92
    ول
    1.82
    ীয়
    1.82
    POSITIVE LOGITS
    ি
    3.38
    yyyy
    3.08
    yyyyyyyy
    2.94
    t
    2.83
    tellers
    2.67
    yy
    2.59
    tu
    2.52
    ي
    2.50
    tl
    2.48
    ுள்ள
    2.47
    Activations Density 0.315%

    No Known Activations