© 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. 157906
    Prev
    Next
    INDEX
    Explanations

    generally bulky

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

    censorship resistance

    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
     Plut
    0.51
     abate
    0.51
     Š
    0.50
     plough
    0.50
     Shetland
    0.49
     acceptor
    0.48
     repatri
    0.48
     Yuri
    0.48
     Chauhan
    0.48
     dinast
    0.48
    POSITIVE LOGITS
    р
    0.49
    тим
    0.47
    ла
    0.47
    ри
    0.46
    ری
    0.46
    ruppe
    0.46
    맵
    0.45
    Travel
    0.45
    ве
    0.44
    孚
    0.43
    Activations Density 0.000%

    No Known Activations