© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144417
    Prev
    Next
    INDEX
    Explanations

    words followed by descriptive or technical terms

    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_16_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
    itate
    0.51
    ischer
    0.50
     améliorer
    0.48
    ischen
    0.46
    ivation
    0.46
     både
    0.46
    Während
    0.46
    ר
    0.46
     ע
    0.45
    ailing
    0.45
    POSITIVE LOGITS
     Third
    0.45
     praise
    0.45
     Praise
    0.44
     Theology
    0.44
    ModuleName
    0.43
    ほ
    0.43
    Tensor
    0.43
     Maternal
    0.43
     myFunction
    0.43
    Translation
    0.42
    Activations Density 0.000%

    No Known Activations