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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 234
    Prev
    Next
    INDEX
    Explanations

    disconnect, swap, breakthrough

    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
    รือ
    1.26
    お子
    1.11
    th
    1.10
    ร
    1.09
    옌
    1.09
    ly
    1.08
    カ
    1.08
     soorten
    1.07
     четы
    1.06
     metabolized
    1.05
    POSITIVE LOGITS
    ărul
    0.89
    𝗔
    0.89
    Y
    0.88
    ির
    0.84
    c
    0.82
    いない
    0.82
    කු
    0.81
    cima
    0.81
    Ｙ
    0.81
    씀
    0.81
    Activations Density 0.846%

    No Known Activations