© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200157
    Prev
    Next
    INDEX
    Explanations

    integrity=" links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    客様
    0.41
    ಳಿತ
    0.39
     pressured
    0.38
    location
    0.38
    基本的に
    0.38
    p
    0.38
    पीड़न
    0.38
    ane
    0.37
     উঠ
    0.37
    m
    0.36
    POSITIVE LOGITS
    ވެ
    0.49
     самому
    0.48
    OFF
    0.48
     систему
    0.47
     Зо
    0.46
    ினான்
    0.44
    ЕР
    0.44
     संहिता
    0.44
     pallet
    0.43
     навчання
    0.43
    Activations Density 0.002%

    No Known Activations