© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8359
    Prev
    Next
    INDEX
    Explanations

    existing literature and research

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    簡
    0.43
     PLoS
    0.42
     MNRAS
    0.42
     Validation
    0.42
    mAb
    0.42
     CERN
    0.42
     Preprint
    0.41
     mAb
    0.41
    䢌
    0.40
    正在
    0.40
    POSITIVE LOGITS
     literature
    1.59
    literature
    1.47
    Literature
    1.30
     Literature
    1.30
     literatura
    1.25
     letteratura
    1.21
     литературы
    1.20
     littérature
    1.19
     literat
    1.18
     литера
    1.16
    Activations Density 0.151%

    No Known Activations