© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8474
    Prev
    Next
    INDEX
    Explanations

    ASCII art faces

    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_31_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
     स्थिर
    0.56
    commun
    0.54
    étique
    0.53
     între
    0.53
    
    0.53
    asign
    0.51
    表中
    0.51
    ങ്ങളില്‍
    0.50
    ø
    0.50
    consumption
    0.50
    POSITIVE LOGITS
     button
    0.55
     zeb
    0.55
    執行
    0.53
     neurom
    0.52
     lij
    0.52
    ီး
    0.51
     Surprise
    0.51
     liz
    0.51
     পাওয়
    0.50
    শিয়ার
    0.50
    Activations Density 0.004%

    No Known Activations