© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98810
    Prev
    Next
    INDEX
    Explanations

    demographic questions

    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
     Erit
    0.42
     Rou
    0.40
    抿
    0.40
    羧
    0.38
     राउ
    0.38
     Brou
    0.37
     Fij
    0.37
    錳
    0.37
     classific
    0.37
     SCSI
    0.37
    POSITIVE LOGITS
     nije
    0.39
     पलट
    0.39
     داده
    0.37
    ായ്
    0.36
    reur
    0.35
     podpor
    0.35
     공
    0.35
    taken
    0.35
    IGA
    0.35
     नष्ट
    0.34
    Activations Density 0.000%

    No Known Activations