© 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. 40-GEMMASCOPE-2-RES-262K
    4. 17811
    Prev
    Next
    INDEX
    Explanations

    international characters

    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_40_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
    Estado
    0.45
    第五
    0.41
    绰
    0.40
    ynchronous
    0.40
    တော့
    0.39
     kinemat
    0.38
    十六章
    0.38
    安倍
    0.38
     رباع
    0.38
    гация
    0.38
    POSITIVE LOGITS
     táo
    0.45
    t
    0.44
     mouthpiece
    0.42
     ধাতু
    0.42
     Seeds
    0.42
     drips
    0.41
     nut
    0.41
    濂
    0.40
     Nut
    0.40
    umin
    0.40
    Activations Density 21.333%

    No Known Activations