© 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. 3444
    Prev
    Next
    INDEX
    Explanations

    manage resources, identities, 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
     וכ
    1.52
    ня
    1.14
     joys
    1.11
    ש
    1.10
     лист
    1.08
    蚪
    1.07
    তবে
    1.04
     hijacked
    1.04
    ,
    1.03
    сей
    0.99
    POSITIVE LOGITS
    يين
    2.03
     remoto
    1.57
    ğlu
    1.51
    ども
    1.46
     doméstica
    1.45
     gestire
    1.44
    т
    1.43
     equilibrio
    1.41
     alcuna
    1.39
     authorizes
    1.37
    Activations Density 0.395%

    No Known Activations