© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36751
    Prev
    Next
    INDEX
    Explanations

    cinematic lighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    شرات
    0.42
     enemigos
    0.41
     forman
    0.41
     Coordinate
    0.40
    তামূলক
    0.40
     Coordinating
    0.39
    قوق
    0.39
     enemigo
    0.38
     Mediator
    0.38
    ɧ
    0.38
    POSITIVE LOGITS
    Cin
    0.52
     cinemat
    0.51
     CIN
    0.51
     Cinema
    0.50
    cinema
    0.50
     Cin
    0.49
    cin
    0.48
     cinema
    0.48
     cin
    0.47
     সিনেমা
    0.46
    Activations Density 0.001%

    No Known Activations