© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 15527
    Prev
    Next
    INDEX
    Explanations

    heli, sex, sand variations

    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
    ﻕ
    1.35
    ل
    1.27
    ﺍ
    1.27
    στα
    1.19
    涜
    1.16
     некоторое
    1.13
    рованных
    1.12
     никакого
    1.10
    жных
    1.09
     koje
    1.07
    POSITIVE LOGITS
    idge
    1.28
    er
    1.10
    aal
    1.10
    я
    1.06
    a
    1.05
    ărat
    1.04
    ați
    1.04
    óng
    1.03
    aat
    1.02
    ette
    1.01
    Activations Density 0.003%

    No Known Activations