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. 44559
    Prev
    Next
    INDEX
    Explanations

    thoroughly followed by adjectives

    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
    ר
    1.95
    ת
    1.77
    ن
    1.72
    ない
    1.64
    นำ
    1.52
    ال
    1.49
    nál
    1.41
    ла
    1.40
    nél
    1.40
    ও
    1.39
    POSITIVE LOGITS
    }">${
    1.29
     längst
    1.24
    %>
    1.23
    cticamente
    1.23
     AppCompat
    1.22
     అయితే
    1.19
     Sovi
    1.15
     Occidental
    1.15
     amusement
    1.14
     Admittedly
    1.13
    Activations Density 0.003%

    No Known Activations