© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4084
    Prev
    Next
    INDEX
    Explanations

    social hardship and desperation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    猬
    2.19
    ු
    2.14
     res
    2.08
     penge
    2.02
    en
    1.98
    ਵਾਈ
    1.96
     prol
    1.95
    ੱਸ
    1.89
     tren
    1.88
     daleko
    1.87
    POSITIVE LOGITS
    ப்பிட
    2.39
    𝚎
    2.33
    𝚑
    2.33
    𝚝
    2.29
    𝚊
    2.25
     pectin
    2.25
     alleviation
    2.21
    AudioFocus
    2.20
    ᅬ
    2.20
     vững
    2.19
    Activations Density 0.132%

    No Known Activations