© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2806
    Prev
    Next
    INDEX
    Explanations

    you say, function as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Evento
    1.32
     afectada
    1.30
    䳕
    1.25
     valoración
    1.23
     afectadas
    1.23
     Nacional
    1.23
     Curso
    1.23
     Grupo
    1.22
     GoName
    1.21
    ⴳ
    1.20
    POSITIVE LOGITS
    computer
    1.16
    you
    1.06
    philosoph
    1.02
    memory
    1.02
    acles
    1.00
     philosophical
    1.00
     beings
    1.00
     uč
    0.99
     memory
    0.99
    sometimes
    0.98
    Activations Density 2.789%

    No Known Activations