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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 268
    Prev
    Next
    INDEX
    Explanations

    listing examples with such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
    __/
    0.99
    jska
    0.98
     Нужно
    0.95
    '}),
    0.95
     recipro
    0.94
    /?
    0.93
     &/
    0.92
    щении
    0.92
    $/
    0.91
    馬上
    0.91
    POSITIVE LOGITS
     as
    2.83
     sebagai
    2.42
     als
    2.08
     como
    2.07
     jako
    2.07
     ως
    2.00
    as
    1.95
     comme
    1.90
    作为
    1.79
     As
    1.77
    Activations Density 1.566%

    No Known Activations