© 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. 59775
    Prev
    Next
    INDEX
    Explanations

    informal blogs

    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
     Wachstum
    0.40
    huang
    0.40
     pertumbuhan
    0.38
    )}_{
    0.38
    *}$
    0.38
     ho
    0.38
    痈
    0.38
     достат
    0.37
    挿
    0.37
     Bevölkerung
    0.37
    POSITIVE LOGITS
    Solid
    0.42
    Ⲉ
    0.40
    irikan
    0.39
     examen
    0.37
    PostBody
    0.37
     Hàm
    0.36
     turns
    0.36
    orneys
    0.36
    turns
    0.35
     omen
    0.35
    Activations Density 0.000%

    No Known Activations