© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60952
    Prev
    Next
    INDEX
    Explanations

    Nico Nico Douga

    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_all/layer_41_width_262k_l0_big
    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
     `'\\
    0.42
    ্স্ট
    0.41
     आफ्टरनून
    0.39
     фаразлары
    0.39
    rath
    0.38
    ráf
    0.38
     AstraZeneca
    0.38
    Prothorax
    0.38
    FBSDKSettings
    0.38
    鵲
    0.38
    POSITIVE LOGITS
     Nico
    0.64
    ニコ
    0.57
    弹
    0.55
     nic
    0.51
    nico
    0.51
     video
    0.49
     coin
    0.46
     Nicolas
    0.46
     Nicolás
    0.46
    彈
    0.44
    Activations Density 0.001%

    No Known Activations