Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1134
    Prev
    Next
    INDEX
    Explanations

    data, samples, or values

    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
    u
    1.21
    U
    1.20
    M
    1.13
    IN
    1.09
    yki
    1.08
    E
    1.08
    Istituto
    1.02
     INSTITUTE
    1.01
    ol
    1.00
    LER
    0.99
    POSITIVE LOGITS
    ти
    1.28
    .
    1.16
    ů
    1.09
     distinguishers
    1.03
    ین
    1.00
    тность
    1.00
    。,
    0.99
    ർ
    0.96
    ты
    0.94
    ,
    0.94
    Activations Density 1.429%

    No Known Activations