© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99429
    Prev
    Next
    INDEX
    Explanations

    zoo animals or services

    np_acts-logits-general · gemini-2.5-flash-lite

    Irritable Bowel Syndrome or groupby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ให้กับ
    0.44
    我们需要
    0.44
    这篇文章
    0.43
    这个人
    0.43
    这两
    0.42
    使用
    0.41
    앰
    0.41
    ゙
    0.40
    记住
    0.39
     அதிகமாக
    0.39
    POSITIVE LOGITS
     shrine
    0.49
     paraît
    0.49
     motos
    0.49
     relive
    0.49
     jsou
    0.46
    gris
    0.46
     è
    0.46
    ocor
    0.46
     chapel
    0.45
     constitue
    0.44
    Activations Density 0.001%

    No Known Activations