© 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. 43374
    Prev
    Next
    INDEX
    Explanations

    representing the

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

    declining groundwater levels

    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
    ඝ
    0.47
    ز
    0.47
    뷸
    0.45
    بلی
    0.43
    ophysics
    0.42
    ણને
    0.42
    த
    0.42
    ๊
    0.41
    рс
    0.41
    گر
    0.41
    POSITIVE LOGITS
     coordination
    0.55
     ordine
    0.49
    Archivo
    0.49
     coordinating
    0.48
     Coordination
    0.48
     insgesamt
    0.48
     authorizations
    0.47
     coordinación
    0.47
     orden
    0.47
     Orden
    0.46
    Activations Density 0.000%

    No Known Activations