© 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. 3961
    Prev
    Next
    INDEX
    Explanations

    branded products

    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
     言っ
    0.43
    页面存档备份
    0.34
    कल्चर
    0.34
    टीशन
    0.33
    甠
    0.32
    न्हें
    0.31
    agamanam
    0.31
    眹
    0.31
    跇
    0.31
     सश
    0.30
    POSITIVE LOGITS
    0.48
    ®
    0.42
    3
    0.41
    5
    0.41
    6
    0.40
     F
    0.39
    1
    0.39
    4
    0.38
     V
    0.38
     latest
    0.38
    Activations Density 0.138%

    No Known Activations