© 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. 28635
    Prev
    Next
    INDEX
    Explanations

    like examples

    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
     ಹಾಗೂ
    0.49
    ↵↵
    0.45
    $(\
    0.38
    Printf
    0.37
    Vega
    0.37
     ซึ่ง
    0.36
    NaF
    0.36
    </em>
    0.36
     จึง
    0.36
    endal
    0.36
    POSITIVE LOGITS
     idk
    0.80
     uh
    0.64
    呃
    0.61
     dunno
    0.56
    嗯
    0.50
     sorta
    0.49
     um
    0.49
     kinda
    0.49
     ehm
    0.48
     digamos
    0.48
    Activations Density 0.007%

    No Known Activations