© 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-262K
    7. 4023
    Prev
    Next
    INDEX
    Explanations

    garbage collection, trash, waste

    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_262k_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
     empê
    1.97
     ağ
    1.91
    要
    1.78
    知道
    1.73
     آیا
    1.68
    َا
    1.67
    SI
    1.65
    รอบ
    1.65
    embang
    1.64
    même
    1.63
    POSITIVE LOGITS
    ક
    1.81
    ных
    1.70
    erweise
    1.62
     hauled
    1.59
     thải
    1.59
     clasp
    1.55
     copolymer
    1.52
    нец
    1.52
    ные
    1.51
     towel
    1.51
    Activations Density 0.114%

    No Known Activations