© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71071
    Prev
    Next
    INDEX
    Explanations

    harmful or illegal requests

    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
     يتم
    0.49
     Quality
    0.48
     Serif
    0.46
    =\{
    0.44
    <-
    0.44
    =
    0.44
    ي
    0.43
    =\"
    0.42
     <-
    0.41
    )=
    0.41
    POSITIVE LOGITS
     그러나
    0.43
    itäts
    0.40
    เร
    0.39
     компен
    0.39
     puso
    0.39
     使っ
    0.39
     완전히
    0.39
    กิจกรรม
    0.38
     capítulos
    0.38
     carcinogenesis
    0.38
    Activations Density 0.010%

    No Known Activations