© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16296
    Prev
    Next
    INDEX
    Explanations

    in front

    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
     Southern
    0.55
     ама
    0.55
     hậu
    0.54
     South
    0.52
     rear
    0.52
    
    0.52
     दक्षिण
    0.51
     백
    0.51
     দক্ষিণ
    0.50
    backslash
    0.50
    POSITIVE LOGITS
     front
    2.39
    Front
    2.06
     Front
    2.00
    前
    1.99
     upfront
    1.97
     FRONT
    1.97
    front
    1.96
    FRONT
    1.90
     davanti
    1.83
    フロント
    1.81
    Activations Density 0.567%

    No Known Activations