© 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. 50526
    Prev
    Next
    INDEX
    Explanations

    years. drive. goals.finals. watt. SI. black. back

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

    creature, towers, songs, device, science

    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
     porridge
    0.49
     sympy
    0.48
    ⟋
    0.47
     processors
    0.46
    借助
    0.46
    >.</
    0.46
    GLIGENCE
    0.45
     kernels
    0.45
     tsp
    0.45
     rigorously
    0.45
    POSITIVE LOGITS
    ado
    0.54
    ED
    0.54
    DA
    0.51
    ADOS
    0.51
    ivos
    0.49
    DE
    0.49
    Ka
    0.49
    Já
    0.49
    KA
    0.48
    ė
    0.48
    Activations Density 0.001%

    No Known Activations