© 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. 44309
    Prev
    Next
    INDEX
    Explanations

    costs of surgery

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

    numbers in lists

    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
    łem
    0.45
     בה
    0.44
    ("");
    0.43
    smtp
    0.43
    ৬৮
    0.43
    .$(
    0.42
    过程
    0.41
    改變
    0.41
    ฝ
    0.41
    每个
    0.41
    POSITIVE LOGITS
     Muslims
    0.43
     Jammu
    0.42
     Arabs
    0.39
     Islamic
    0.38
     justiciable
    0.38
     Marines
    0.37
     Arabic
    0.36
    ْس
    0.36
     Africans
    0.36
     ähm
    0.36
    Activations Density 0.005%

    No Known Activations