© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5543
    Prev
    Next
    INDEX
    Explanations

    mathematical exponents and powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
    ď
    0.74
     explain
    0.66
    explain
    0.63
     छा
    0.63
    近期
    0.59
    ʊ
    0.59
    ौल
    0.59
     Só
    0.58
     삶
    0.58
     einzelnen
    0.57
    POSITIVE LOGITS
    "^
    1.25
    щена
    1.09
    ਕ
    1.04
    $^
    1.02
    __."
    1.01
    дию
    0.98
     Garden
    0.98
    '^
    0.98
     Gardens
    0.97
    钬
    0.97
    Activations Density 0.020%

    No Known Activations