© 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-262K
    7. 23127
    Prev
    Next
    INDEX
    Explanations

    Code definition markers

    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
    龴
    0.38
    シング
    0.36
    oreal
    0.36
     samud
    0.35
    ൃ
    0.35
    ᚑ
    0.34
    ambia
    0.34
     सिंगिंग
    0.34
    )){
    0.34
    æng
    0.34
    POSITIVE LOGITS
    Execute
    0.47
     Execute
    0.44
     execute
    0.42
     crée
    0.41
     tack
    0.40
     Robbie
    0.40
    adder
    0.40
     adder
    0.40
    PON
    0.40
     celebrated
    0.39
    Activations Density 0.000%

    No Known Activations