© 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. 20233
    Prev
    Next
    INDEX
    Explanations

    transfer PIN, known vulnerabilities, Foundations

    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
    С
    0.48
    查看
    0.46
    ер
    0.46
    ве
    0.45
    р
    0.45
    看一下
    0.44
    정
    0.44
    пом
    0.43
    у
    0.43
    ਲ
    0.43
    POSITIVE LOGITS
     nebude
    0.48
     egensk
    0.46
     estr
    0.42
     hänen
    0.42
     Zeichen
    0.42
     Stabil
    0.42
     avulla
    0.41
     blockage
    0.40
     cez
    0.40
     tuleb
    0.40
    Activations Density 0.007%

    No Known Activations