© 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. 12-GEMMASCOPE-2-RES-16K
    7. 9508
    Prev
    Next
    INDEX
    Explanations

    discussing destruction or danger

    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
    j
    1.11
    ра
    1.03
    ra
    0.98
    b
    0.97
    r
    0.90
    อบ
    0.89
    н
    0.88
    .
    0.86
    ↵
    0.85
    ci
    0.84
    POSITIVE LOGITS
     którego
    0.97
     shameless
    0.93
     долларов
    0.92
     cyberpunk
    0.91
     selber
    0.91
     cashmere
    0.90
     которые
    0.89
     bookcases
    0.89
     lysosomes
    0.89
     смотреть
    0.88
    Activations Density 0.001%

    No Known Activations