© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83687
    Prev
    Next
    INDEX
    Explanations

    aromagnetism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     camels
    0.52
     designates
    0.52
    <0xE2>
    0.49
     counties
    0.47
     radian
    0.47
     groupings
    0.46
    еди
    0.45
     lawfully
    0.45
     Cortés
    0.45
    ﻧ
    0.45
    POSITIVE LOGITS
    ptr
    0.49
    žno
    0.48
    鈿
    0.47
    neither
    0.46
    besides
    0.46
    ensitivity
    0.45
    letscher
    0.45
    exhaustive
    0.45
     Importantly
    0.44
    development
    0.43
    Activations Density 0.010%

    No Known Activations