© 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. 22097
    Prev
    Next
    INDEX
    Explanations

    acceleration, rates, and derivatives

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

    derivative of physics quantities

    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
     afstand
    0.51
     uży
    0.50
     anvä
    0.49
     हाथ
    0.48
     والم
    0.46
     Մ
    0.46
     Владими
    0.46
     ދ
    0.46
     Володи
    0.45
    NaHCO
    0.45
    POSITIVE LOGITS
     triples
    0.40
     driven
    0.39
     provocative
    0.39
     rates
    0.38
     dashboard
    0.38
     disordered
    0.38
     architects
    0.38
    <strong>
    0.37
     cascade
    0.37
     intensities
    0.37
    Activations Density 0.005%

    No Known Activations