© 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. 190742
    Prev
    Next
    INDEX
    Explanations

    death of loved ones

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

    questions about specific topics

    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
    awar
    0.47
     podstawie
    0.47
    έρα
    0.46
     Fungsi
    0.45
    gın
    0.42
    舧
    0.42
    گیر
    0.42
    绫
    0.42
     intéressante
    0.40
     podstaw
    0.40
    POSITIVE LOGITS
     CCSDT
    0.48
     JD
    0.48
     Pepsi
    0.47
     trimming
    0.45
     kidneys
    0.44
     caries
    0.44
     catheters
    0.44
     “(
    0.44
     strikeouts
    0.43
     behem
    0.43
    Activations Density 0.001%

    No Known Activations