© 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. 76449
    Prev
    Next
    INDEX
    Explanations

    describes subsequent words

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

    language shapes reality

    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
     la
    0.53
    лық
    0.49
    ي
    0.48
    لا
    0.47
     a
    0.46
     Comedy
    0.46
     obi
    0.45
    曛
    0.45
     Royal
    0.45
     royal
    0.45
    POSITIVE LOGITS
    hosted
    0.52
    fought
    0.46
    stimulating
    0.46
    developed
    0.45
    attacking
    0.45
     utilizamos
    0.45
     সিস্টেম
    0.45
    лянчук
    0.44
    utiliser
    0.43
     سسٹم
    0.43
    Activations Density 0.001%

    No Known Activations