© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23254
    Prev
    Next
    INDEX
    Explanations

    obviously, of course, both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     amid
    0.39
    amid
    0.39
     निरी
    0.38
    而非
    0.38
     বিশেষজ্ঞদের
    0.37
    compared
    0.36
     travailleurs
    0.36
    ᆫ
    0.36
    而不是
    0.36
     вместо
    0.36
    POSITIVE LOGITS
     oczywiście
    0.53
     ovviamente
    0.53
     évidemment
    0.46
     sowohl
    0.42
    を使って
    0.42
    ですし
    0.42
     obviously
    0.41
    を使用して
    0.41
     당연
    0.41
     både
    0.40
    Activations Density 0.044%

    No Known Activations