© 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-65K
    7. 55225
    Prev
    Next
    INDEX
    Explanations

    internal support structure

    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_65k_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
     മതി
    0.48
    leaves
    0.43
    Leaves
    0.40
    钺
    0.40
     roofs
    0.39
     pintu
    0.38
     livello
    0.38
     foliis
    0.37
    प्पी
    0.37
    酯
    0.37
    POSITIVE LOGITS
     карка
    0.79
     frame
    0.70
     framework
    0.70
     skeleton
    0.61
    Framework
    0.61
     Frame
    0.59
     backing
    0.59
     frames
    0.59
    framework
    0.59
     armature
    0.59
    Activations Density 0.030%

    No Known Activations