© 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. 16831
    Prev
    Next
    INDEX
    Explanations

    website, internet, or organizational terms

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

    informal explanations

    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
     ponto
    0.56
    берриз
    0.54
    ันท
    0.50
    ค์
    0.49
    裘
    0.48
    दरअसल
    0.47
    และ
    0.47
    ้าย
    0.47
    เพราะ
    0.47
    कने
    0.47
    POSITIVE LOGITS
    γ
    0.50
     replication
    0.50
    aboration
    0.45
    具
    0.44
    insley
    0.43
    VOA
    0.43
     muod
    0.42
    illard
    0.42
     supplements
    0.42
    可行
    0.42
    Activations Density 0.000%

    No Known Activations