© 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. 16117
    Prev
    Next
    INDEX
    Explanations

    problems and matters

    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
    っていた
    0.75
    м
    0.71
     вычисли
    0.71
    이란
    0.70
    是一種
    0.66
    っている
    0.64
    恙
    0.64
    ため
    0.64
    Q
    0.62
    是一种
    0.61
    POSITIVE LOGITS
     issues
    1.05
     Issues
    1.05
     arise
    0.95
    issues
    0.93
     arisen
    0.88
     arose
    0.87
     deserving
    0.84
     merit
    0.82
    Issues
    0.82
     delicate
    0.82
    Activations Density 0.066%

    No Known Activations