© 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-16K
    7. 12201
    Prev
    Next
    INDEX
    Explanations

    depending on conditions or choices

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

    whichever, whatever, depending

    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_16k_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
    এবং
    0.40
    也是
    0.40
    และความ
    0.40
    හ
    0.39
    我也是
    0.38
    这也是
    0.37
    cki
    0.36
    సాయ
    0.36
    ሚ
    0.36
     Bellamy
    0.35
    POSITIVE LOGITS
     whichever
    1.55
     depending
    1.46
    いずれ
    1.39
    depending
    1.34
    どちら
    1.29
     dependiendo
    1.17
     Depending
    1.09
    Depending
    1.05
     tergantung
    1.02
     зависит
    1.01
    Activations Density 0.366%

    No Known Activations