© 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. 212485
    Prev
    Next
    INDEX
    Explanations

    malicious use of information and technologies

    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
    坵
    0.49
    人間
    0.46
     Đà
    0.46
     Hailey
    0.44
     placée
    0.43
    䣨
    0.42
    番組
    0.42
    节目
    0.41
     conforto
    0.41
     Rhonda
    0.41
    POSITIVE LOGITS
    dual
    0.84
     dual
    0.82
    Dual
    0.80
     misuse
    0.79
     Dual
    0.74
     technologies
    0.70
     duality
    0.68
     tecnologias
    0.63
     misused
    0.63
     tecnologie
    0.62
    Activations Density 0.147%

    No Known Activations