© 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. 129266
    Prev
    Next
    INDEX
    Explanations

    idiomatic expressions and cultural references

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

    water in cup

    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
     י
    0.55
    са
    0.51
     ח
    0.50
     ס
    0.50
    WILL
    0.48
     ג
    0.47
     я
    0.46
     א
    0.46
    с
    0.46
     лю
    0.45
    POSITIVE LOGITS
     idol
    0.42
     pelatihan
    0.42
     dormitory
    0.42
     intenta
    0.42
     boarding
    0.41
     anschließend
    0.41
     kelompok
    0.41
     qualcuno
    0.41
     dormitorios
    0.40
     alguém
    0.40
    Activations Density 0.000%

    No Known Activations