© 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. 42271
    Prev
    Next
    INDEX
    Explanations

    Mass gatherings safety

    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
     Polynomial
    0.47
     señ
    0.46
    环境
    0.45
     cerevisiae
    0.45
    产量
    0.44
    颜
    0.43
     piel
    0.43
     حوصل
    0.42
    依然
    0.42
     producent
    0.42
    POSITIVE LOGITS
     investigative
    0.49
     bridges
    0.43
     мелдеш
    0.43
     hypnosis
    0.42
     robotic
    0.42
     approximating
    0.41
    units
    0.41
     repetitive
    0.41
     collars
    0.40
    멜
    0.40
    Activations Density 0.000%

    No Known Activations