© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137290
    Prev
    Next
    INDEX
    Explanations

    radiate, rotate, accelerate

    np_acts-logits-general · gemini-2.5-flash-lite

    visualize materials and predict behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    飜
    0.46
    arser
    0.45
     diferentes
    0.44
    btnUn
    0.44
    しの
    0.44
    কেল
    0.41
    नु
    0.41
     RNAs
    0.41
    Scaling
    0.41
    कों
    0.41
    POSITIVE LOGITS
    oud
    0.49
    radiative
    0.49
    rotating
    0.48
    atur
    0.48
    à
    0.47
     fabri
    0.46
     ރ
    0.46
     archi
    0.45
     खि
    0.44
    archiwizowane
    0.44
    Activations Density 0.000%

    No Known Activations