© 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. 18362
    Prev
    Next
    INDEX
    Explanations

    entry was posted

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

    code, punctuation, and technical terms

    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
     injustices
    0.61
    льность
    0.56
     injustice
    0.54
    λογή
    0.49
     indignation
    0.49
    こと
    0.46
    ｌ
    0.46
     intimidating
    0.44
    說
    0.44
    lichkeit
    0.44
    POSITIVE LOGITS
    ANE
    0.69
     કરતા
    0.51
    ÁN
    0.50
    ASHI
    0.50
    +"
    0.49
    KD
    0.48
    THREADS
    0.48
     করিয়
    0.48
    آ
    0.48
     هت
    0.47
    Activations Density 0.001%

    No Known Activations