© 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. 14613
    Prev
    Next
    INDEX
    Explanations

    drug use, abuse, or manufacturing

    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
    ─────
    1.19
    ெடு
    1.17
     ү
    1.13
    ெடுக்க
    1.13
    ﻲ
    1.11
     niemals
    1.09
    (',
    1.08
    (",
    1.02
    ˖
    1.02
    ণিজ
    1.01
    POSITIVE LOGITS
    na
    1.37
    et
    1.27
    ta
    1.09
    Ara
    1.06
    en
    1.05
    es
    1.05
    ne
    1.02
    men
    1.02
     Azərbaycan
    0.99
    me
    0.99
    Activations Density 0.079%

    No Known Activations