© 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. 30326
    Prev
    Next
    INDEX
    Explanations

    interval '7 days' or sequence length

    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
    一個
    1.29
     này
    1.28
    אן
    1.27
     pêche
    1.23
     varía
    1.22
    的
    1.21
    து
    1.19
     possède
    1.19
    种
    1.19
    २
    1.18
    POSITIVE LOGITS
    s
    1.69
    de
    1.51
    ுங்கள்
    1.51
    propri
    1.30
    syair
    1.29
     (
    1.23
     основы
    1.23
    ுமா
    1.23
    camp
    1.22
    cord
    1.21
    Activations Density 0.024%

    No Known Activations