© 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. 6710
    Prev
    Next
    INDEX
    Explanations

    challenging norms, systems, or ideas

    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
    ار
    1.76
    ن
    1.73
    //"
    1.64
    '/>
    1.59
    '*
    1.55
     Balliye
    1.52
    ات
    1.51
    \%
    1.49
    \%$
    1.47
    '");
    1.44
    POSITIVE LOGITS
    breaking
    1.44
     Mod
    1.34
     Alles
    1.26
     beraber
    1.25
    нг
    1.24
    ิ
    1.22
    tır
    1.21
     Challenge
    1.20
    bak
    1.19
    ls
    1.18
    Activations Density 0.171%

    No Known Activations