© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3776
    Prev
    Next
    INDEX
    Explanations

    asking for details

    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_65k_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
    rive
    0.43
    menuid
    0.42
    τή
    0.42
    ZE
    0.42
    ائيه
    0.41
    বৃদ্ধ
    0.41
    可以直接
    0.40
    믄
    0.39
    miss
    0.39
    wie
    0.39
    POSITIVE LOGITS
     diagnóstico
    0.49
     ஊக்கு
    0.49
    Iris
    0.48
     उन्मूलन
    0.47
     alegre
    0.47
     statistik
    0.46
     fantas
    0.44
     നിങ്ങൾ
    0.44
     ôm
    0.44
     Dens
    0.44
    Activations Density 0.018%

    No Known Activations