© 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. 47939
    Prev
    Next
    INDEX
    Explanations

    multilingual text elements

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

    mode collapse

    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
    *(
    0.47
     لين
    0.45
    mee
    0.42
    (
    0.42
     उतर
    0.41
    rainfall
    0.41
    馳
    0.41
    ﾗ
    0.40
    但也
    0.40
    nier
    0.39
    POSITIVE LOGITS
     adulter
    0.54
    လှ
    0.48
    どちら
    0.47
     inventions
    0.46
     cookware
    0.45
     estratégico
    0.45
    ři
    0.44
     étrang
    0.44
    akukannya
    0.44
    ะ
    0.44
    Activations Density 0.000%

    No Known Activations