© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3112
    Prev
    Next
    INDEX
    Explanations

    mitigating damage, stronger language, machines smarter

    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
     guaranteeing
    0.43
     only
    0.40
     merely
    0.39
     convolutional
    0.38
    全ての
    0.37
     aussch
    0.37
     G
    0.36
     enzimas
    0.36
     wszystkie
    0.36
     triples
    0.36
    POSITIVE LOGITS
     ανθρώ
    0.49
    个人
    0.47
    거나
    0.47
     человеком
    0.45
    하거나
    0.45
     algún
    0.44
     людьми
    0.44
    慝
    0.44
     žmon
    0.44
    沌
    0.44
    Activations Density 0.249%

    No Known Activations