© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3233
    Prev
    Next
    INDEX
    Explanations

    hiding and escaping

    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_16_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
    s
    1.01
    st
    0.95
    r
    0.91
    d
    0.86
    w
    0.75
    0
    0.75
    p
    0.71
    b
    0.67
    x
    0.67
    v
    0.65
    POSITIVE LOGITS
    at
    0.96
    ༦
    0.83
     escapes
    0.79
    م
    0.76
    ır
    0.73
    ٹ
    0.73
    ۶
    0.72
    নার
    0.71
     refuge
    0.71
     fug
    0.70
    Activations Density 0.090%

    No Known Activations