© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85650
    Prev
    Next
    INDEX
    Explanations

    cities and deals

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

    story, stories, untold

    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
    Negative Logits
    tiktok
    0.47
    eluarkan
    0.46
    赈
    0.46
    ไง
    0.45
    ImgBoard
    0.45
    पर्स
    0.44
     контроли
    0.43
     मनोहर
    0.43
    肃
    0.43
    姗
    0.43
    POSITIVE LOGITS
     Viejo
    0.46
     competed
    0.45
     converges
    0.45
     Questa
    0.44
     excavated
    0.43
     acheté
    0.43
     playback
    0.43
     achats
    0.43
     Nemat
    0.42
     bounded
    0.41
    Activations Density 0.000%

    No Known Activations