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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3948
    Prev
    Next
    INDEX
    Explanations

    step or stand followed by preposition

    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_16k_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
    ри
    0.71
    ן
    0.71
    ار
    0.63
    িন
    0.63
    на
    0.62
    цы
    0.60
    p
    0.59
    бе
    0.59
    リ
    0.58
    দের
    0.57
    POSITIVE LOGITS
    屹
    0.99
     खड़ा
    0.97
     खड़े
    0.96
     ovation
    0.93
     Standing
    0.88
     standing
    0.88
     Stand
    0.82
     നിൽ
    0.80
    stands
    0.79
     berdiri
    0.79
    Activations Density 0.100%

    No Known Activations