© 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. 41-GEMMASCOPE-2-RES-262K
    7. 102439
    Prev
    Next
    INDEX
    Explanations

    activation function

    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_all/layer_41_width_262k_l0_big
    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
    {(-
    0.40
    }{}
    0.38
    の説明
    0.37
     mask
    0.37
    ブレ
    0.36
    膜
    0.36
     dropout
    0.36
    interesting
    0.36
     बेट
    0.36
     explanatory
    0.35
    POSITIVE LOGITS
     Señor
    0.42
     sanguí
    0.40
     ছ
    0.40
    dataFile
    0.40
    만한
    0.40
     Política
    0.40
     Excuse
    0.40
     Sở
    0.40
     Exhibit
    0.39
     Senhor
    0.39
    Activations Density 0.000%

    No Known Activations