© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    lp Address or Base

    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
    siege
    0.42
    牫
    0.41
    ைகளால்
    0.40
    ossed
    0.39
    ه
    0.37
    ال
    0.37
    াহ
    0.37
    favorites
    0.36
     flaves
    0.36
    ন্ম
    0.36
    POSITIVE LOGITS
     leap
    0.45
     Lap
    0.42
    Frog
    0.42
     lip
    0.41
     осо
    0.41
     লিপ
    0.41
     LP
    0.40
     LPS
    0.40
     frog
    0.40
    🐸
    0.40
    Activations Density 0.001%

    No Known Activations