Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 387
    Prev
    Next
    INDEX
    Explanations

    URLs and websites

    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
    ∖
    0.19
     मांसपेश
    0.18
    ั้ง
    0.17
    ependant
    0.17
     repurposed
    0.16
     Ideally
    0.16
     incompressible
    0.16
     அள
    0.16
    ائق
    0.16
     bypassed
    0.16
    POSITIVE LOGITS
    7
    0.29
    8
    0.27
    9
    0.26
    6
    0.26
    4
    0.23
    5
    0.23
    3
    0.22
    2
    0.19
    ۱۹
    0.18
    १९
    0.18
    Activations Density 0.095%

    No Known Activations