© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135775
    Prev
    Next
    INDEX
    Explanations

    criticized or regulate

    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
    Not in Any Lists

    No Comments

    Negative Logits
     intracellular
    0.42
    賖
    0.42
     அ
    0.42
     особо
    0.41
     να
    0.41
    漕
    0.41
     musicales
    0.40
     cardiomy
    0.40
     zyg
    0.40
    ət
    0.40
    POSITIVE LOGITS
    basis
    0.38
    Duty
    0.36
    شنا
    0.36
    Desired
    0.36
    icas
    0.36
    Employer
    0.35
    Carrier
    0.35
    见
    0.35
    identifier
    0.35
    Plane
    0.35
    Activations Density 0.000%

    No Known Activations