© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2566
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     ખાસ
    0.72
    عبة
    0.71
    olino
    0.67
    鍗
    0.67
     appreciably
    0.67
     iremos
    0.67
     últimos
    0.66
    ፦
    0.66
     جوړ
    0.65
     предназна
    0.64
    POSITIVE LOGITS
     escort
    0.76
     estimates
    0.73
     humanities
    0.72
     advisory
    0.71
     ideology
    0.70
     Est
    0.69
     circles
    0.69
     ideologies
    0.68
     prioritizing
    0.67
     quotes
    0.66
    Activations Density 0.114%

    No Known Activations