© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30402
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and structure

    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
     стран
    0.51
     बहुतेक
    0.49
     Strange
    0.43
    敒
    0.43
     অদ্ভুত
    0.42
     semblent
    0.42
    珴
    0.41
    Strange
    0.41
    伀
    0.40
    strange
    0.39
    POSITIVE LOGITS
     ontological
    0.49
     transcends
    0.49
     cranial
    0.47
     synerg
    0.47
     seepage
    0.47
     cosmic
    0.46
     fascist
    0.46
     metaphysical
    0.46
     accessor
    0.46
     artisanal
    0.45
    Activations Density 0.002%

    No Known Activations