© 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. 184347
    Prev
    Next
    INDEX
    Explanations

    delivery, recyclable, logistics

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

    primary region or branch

    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
     ફરી
    0.50
     રૂ
    0.49
     ವೈ
    0.48
     અમને
    0.48
     フ
    0.47
     потря
    0.46
     ರೋ
    0.46
     九
    0.45
     フランス
    0.44
    omány
    0.44
    POSITIVE LOGITS
     deprivation
    0.52
     spins
    0.48
     changes
    0.47
     adopted
    0.46
     cards
    0.45
     accumulation
    0.45
     évent
    0.44
    تمد
    0.44
     accumulations
    0.44
     estud
    0.43
    Activations Density 0.001%

    No Known Activations