© 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. 139295
    Prev
    Next
    INDEX
    Explanations

    programmed AI safety constraints

    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
     bát
    0.44
    포츠
    0.43
    峎
    0.43
     whereupon
    0.43
     historie
    0.42
     Hiroshima
    0.42
     Ono
    0.41
     ጥሩ
    0.40
    ம்ப
    0.40
    ostante
    0.40
    POSITIVE LOGITS
    🔥🔥
    0.41
     Priorities
    0.40
    ))
    0.39
     Меня
    0.39
    不仅仅
    0.39
     uygulam
    0.38
     COMPLEXES
    0.37
    着
    0.37
     replicated
    0.37
    https
    0.37
    Activations Density 0.025%

    No Known Activations