© 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. 208388
    Prev
    Next
    INDEX
    Explanations

    nonexistent charities

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

    disclaimers and limitations

    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
    截
    0.49
    。
    0.48
    利用
    0.46
    从
    0.45
    用
    0.44
    ῎
    0.44
    ใส่
    0.43
    使用
    0.43
    最多
    0.43
    注
    0.43
    POSITIVE LOGITS
     बेरोजगार
    0.49
    azał
    0.49
     tuần
    0.48
     pełni
    0.47
     সপ্তাহ
    0.47
     BlogPost
    0.46
    ים
    0.45
     बेरोजगारी
    0.45
    ajā
    0.45
     വ്യത്യ
    0.45
    Activations Density 0.001%

    No Known Activations