© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30563
    Prev
    Next
    INDEX
    Explanations

    safety guidlines violation

    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
     otherwise
    0.39
     facets
    0.39
     devotes
    0.39
     initially
    0.39
     deviceInfo
    0.37
    附加
    0.37
    u
    0.36
     subsequently
    0.36
    Herd
    0.36
    해야
    0.36
    POSITIVE LOGITS
     плюс
    0.57
     प्लस
    0.46
     PLUS
    0.44
     купить
    0.42
     खासकर
    0.42
     खतरनाक
    0.42
     Plus
    0.41
     +
    0.40
     Además
    0.40
     עם
    0.40
    Activations Density 0.098%

    No Known Activations