© 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. 32595
    Prev
    Next
    INDEX
    Explanations

    amenities and services

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

    words and phrases

    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
    positroid
    0.50
    നാ
    0.50
     移動
    0.49
    姍
    0.49
    魟
    0.49
    偒
    0.48
    MSFont
    0.46
    пикир
    0.46
    龇
    0.46
    发育
    0.46
    POSITIVE LOGITS
     up
    0.59
    0.58
     first
    0.56
    up
    0.54
     net
    0.52
    ut
    0.51
     supply
    0.50
     fue
    0.50
     was
    0.49
     duty
    0.49
    Activations Density 0.000%

    No Known Activations