© 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. 161875
    Prev
    Next
    INDEX
    Explanations

    housing and living spaces

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

    freedom and legality

    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
     rhythmic
    0.51
    \
    0.50
    aro
    0.49
     her
    0.48
     Boys
    0.48
     Pablo
    0.48
    ot
    0.48
     cadet
    0.48
     familial
    0.46
     Daniel
    0.45
    POSITIVE LOGITS
     поча
    0.53
     προβ
    0.52
     ডিজাইন
    0.50
     회
    0.49
     обу
    0.49
     ხელ
    0.49
     پیش
    0.49
     مہ
    0.48
    цима
    0.48
    ﻀ
    0.48
    Activations Density 0.001%

    No Known Activations