© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2995
    Prev
    Next
    INDEX
    Explanations

    certainly, Form, wing, Take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    િ
    1.11
    ج
    0.88
    .
    0.87
     Rou
    0.79
    COME
    0.79
    ﻣ
    0.77
    ش
    0.77
    Pe
    0.74
     Pawan
    0.73
    7
    0.73
    POSITIVE LOGITS
     spezi
    1.04
    gray
    1.02
     gray
    0.88
    aar
    0.88
    জগ
    0.87
     möglicherweise
    0.86
     ആയി
    0.84
    arq
    0.84
     quería
    0.83
    ാരണ
    0.83
    Activations Density 0.000%

    No Known Activations