© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34896
    Prev
    Next
    INDEX
    Explanations

    food insecurity

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

    descriptions of charity events, donation drives, and community aid programs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    -1.63
    ,
    -1.63
     on
    -1.61
     (
    -1.30
     m
    -1.29
     in
    -1.29
    m
    -1.27
     p
    -1.27
    znym
    -1.27
     
    -1.26
    POSITIVE LOGITS
     ویتامین
    1.74
    ﻻ
    1.45
     Wednesday
    1.43
     décontract
    1.41
     help
    1.38
     aiutare
    1.35
     Monday
    1.35
     envoyer
    1.34
     usein
    1.34
     витами
    1.34
    Activations Density 0.020%

    No Known Activations