© 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. 181870
    Prev
    Next
    INDEX
    Explanations

    Budapest Committee screen

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

    listing required items

    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
     tersedia
    0.50
     dokumen
    0.50
    ﻀ
    0.47
     consolidate
    0.47
     bilangan
    0.46
     rezat
    0.46
     disegnare
    0.46
     DOWNLOAD
    0.46
     singoli
    0.46
     محاضرات
    0.45
    POSITIVE LOGITS
    以为
    0.50
    ه
    0.47
     or
    0.46
    诸
    0.46
    im
    0.46
    丧
    0.46
    虔
    0.45
    er
    0.45
    ich
    0.44
    ፖ
    0.44
    Activations Density 0.001%

    No Known Activations