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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14181
    Prev
    Next
    INDEX
    Explanations

    I. list item introducer

    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
    ">⁢</
    0.18
    amatkan
    0.18
     impedir
    0.18
    níci
    0.18
     vínculos
    0.18
     Estou
    0.18
     imediatamente
    0.17
     ايجاد
    0.17
     unreachable
    0.17
    特定の
    0.17
    POSITIVE LOGITS
    *:
    0.28
    ულ
    0.22
    .(
    0.22
     him
    0.22
    8
    0.22
    .):
    0.21
    ]:
    0.21
    }:
    0.21
    *.
    0.21
    asures
    0.21
    Activations Density 0.018%

    No Known Activations