© 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. 9452
    Prev
    Next
    INDEX
    Explanations

    Gyeongbokgung Palace

    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
     Uttarakhand
    1.02
    গ্রাফ
    0.91
     Congregation
    0.89
    рует
    0.83
     Akufo
    0.82
    ল
    0.81
     Metropolitan
    0.80
    ettha
    0.79
    ತ
    0.79
     linemen
    0.79
    POSITIVE LOGITS
    CO
    0.84
     eingestellt
    0.83
     benötigen
    0.80
    BE
    0.79
    RE
    0.76
     spezielle
    0.75
    im
    0.75
    Be
    0.75
     bekannte
    0.75
     bekommen
    0.74
    Activations Density 0.001%

    No Known Activations