© 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. 28827
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations on variables

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

    `+` or `*` after variables

    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
     vix
    0.49
    мя
    0.47
    ডে
    0.44
    धपुर
    0.43
     rins
    0.43
     lights
    0.42
     মি
    0.41
     জ
    0.41
     পরই
    0.41
     Foods
    0.41
    POSITIVE LOGITS
    確立
    0.46
     konflikt
    0.46
    anbul
    0.43
    従って
    0.42
    ۔
    0.42
    خواهد
    0.41
    ｏ
    0.41
     völlig
    0.41
     سوف
    0.41
     solely
    0.40
    Activations Density 0.000%

    No Known Activations