© 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. 6571
    Prev
    Next
    INDEX
    Explanations

    demonstrates, lost, skating, coffee, rain, fall

    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
     fração
    0.51
    }+\
    0.49
     phosphorylated
    0.48
     recombinant
    0.46
     udah
    0.46
     signifikan
    0.46
     grafo
    0.46
     constraining
    0.45
    ⛹
    0.45
     degraded
    0.45
    POSITIVE LOGITS
    들
    0.40
     plenty
    0.39
    kiss
    0.39
    疯
    0.39
    妩
    0.39
    cnt
    0.38
    CCN
    0.38
    stringify
    0.37
    slug
    0.37
     Ricardo
    0.37
    Activations Density 0.001%

    No Known Activations