© 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. 16-GEMMASCOPE-2-RES-262K
    7. 140468
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving powers

    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
    he
    0.98
    2
    0.80
    and
    0.79
    al
    0.77
    um
    0.76
    are
    0.75
    ため
    0.75
    ้ง
    0.72
    1
    0.71
    it
    0.71
    POSITIVE LOGITS
    J
    0.79
     attenuate
    0.73
     concealing
    0.69
    К
    0.69
    X
    0.66
    ем
    0.64
     incarcer
    0.64
    ఫో
    0.64
     decreases
    0.63
     excruciating
    0.63
    Activations Density 0.000%

    No Known Activations