© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 37651
    Prev
    Next
    INDEX
    Explanations

    little + descriptive adjective

    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
     ennek
    1.66
     honti
    1.55
    שו
    1.55
     persones
    1.54
    ᅭ
    1.52
     amelyek
    1.51
    苾
    1.50
    LER
    1.48
    している
    1.47
    ὧ
    1.47
    POSITIVE LOGITS
    ल
    1.94
    ви
    1.77
    ی
    1.76
    ről
    1.73
    ously
    1.72
    lighting
    1.67
    ant
    1.58
    räume
    1.52
    ವ
    1.50
    та
    1.49
    Activations Density 0.017%

    No Known Activations