© 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-262K
    4. 9102
    Prev
    Next
    INDEX
    Explanations

    specify or whether to

    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_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
    1
    1.21
     of
    1.17
    ,
    1.16
    of
    1.12
     or
    1.01
    7
    0.99
     but
    0.96
    2
    0.96
    9
    0.93
    and
    0.92
    POSITIVE LOGITS
     koristiti
    1.20
     ഉപയോഗ
    1.09
    就可以
    1.06
    ständig
    1.05
     možete
    1.04
    ówno
    1.04
     옵
    1.04
    yendo
    1.02
     парамет
    1.02
     사항
    1.02
    Activations Density 0.740%

    No Known Activations