© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14685
    Prev
    Next
    INDEX
    Explanations

    Protection Program, greed is good, Blue City, Pair Encoding, you song

    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
    F
    0.93
    K
    0.91
    J
    0.84
    N
    0.81
    B
    0.80
    P
    0.79
    ="
    0.79
    :
    0.77
    한
    0.76
    Z
    0.75
    POSITIVE LOGITS
     you
    0.92
     of
    0.88
     on
    0.77
    ן
    0.75
    achron
    0.72
     to
    0.72
     protruding
    0.71
     conund
    0.71
    ین
    0.71
     στα
    0.70
    Activations Density 0.000%

    No Known Activations