© 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-16K
    4. 1078
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ar
    1.67
    ان
    1.49
    ن
    1.48
    ಾ
    1.44
     angka
    1.41
     volna
    1.39
    zelfde
    1.33
    かで
    1.31
    った
    1.30
    ار
    1.29
    POSITIVE LOGITS
    ﻮ
    1.27
     Далее
    1.24
     Như
    1.23
     Рассмотрим
    1.23
    ני
    1.22
    지
    1.19
     здійсню
    1.16
     대해
    1.16
     Altogether
    1.14
     withstand
    1.08
    Activations Density 0.069%

    No Known Activations