© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31665
    Prev
    Next
    INDEX
    Explanations

    illegal activities or prostitution

    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_40_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
     условиях
    0.41
     buenos
    0.40
     }+
    0.39
    शियम
    0.38
    揸
    0.38
    scissors
    0.38
    엄
    0.38
    삼성
    0.38
    clipboard
    0.38
    ಮೆ
    0.37
    POSITIVE LOGITS
     into
    0.61
    into
    0.52
    Into
    0.50
     converts
    0.46
     Into
    0.42
     INTO
    0.40
     overview
    0.40
     Vand
    0.39
    转换为
    0.38
     convertido
    0.38
    Activations Density 0.000%

    No Known Activations