© 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. 131200
    Prev
    Next
    INDEX
    Explanations

    search define

    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
     watertight
    0.43
    сторі
    0.41
     கீ
    0.41
     Ears
    0.41
    ീയ
    0.40
    StudentRecord
    0.40
    EndOf
    0.39
    斂
    0.38
     গাড়ীতে
    0.38
    serializing
    0.37
    POSITIVE LOGITS
     प्रेग्न
    0.39
    embre
    0.38
     cabello
    0.38
    anned
    0.38
     погру
    0.37
    inness
    0.36
    жба
    0.36
     radicales
    0.36
     lookup
    0.36
     perform
    0.35
    Activations Density 0.001%

    No Known Activations