© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90903
    Prev
    Next
    INDEX
    Explanations

    here's a breakdown

    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_31_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
     ר
    0.52
    ר
    0.52
     individualized
    0.49
     protecting
    0.47
     iron
    0.47
     weathering
    0.46
     ornamented
    0.46
    乞
    0.46
     מק
    0.45
     כל
    0.44
    POSITIVE LOGITS
     Ey
    0.44
    googleapis
    0.41
     Meh
    0.41
     Moved
    0.41
     Dos
    0.40
     Ontario
    0.39
     Rasmussen
    0.39
    晫
    0.39
     Rik
    0.39
    ：
    0.39
    Activations Density 0.000%

    No Known Activations