© 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. 135424
    Prev
    Next
    INDEX
    Explanations

    comprehending Languages

    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
    Pyrimidine
    0.46
     жизнен
    0.39
    regnum
    0.38
     solvency
    0.38
    <unused3>
    0.38
    绰
    0.37
     تاني
    0.37
    draggable
    0.37
    祿
    0.37
     세율
    0.36
    POSITIVE LOGITS
     Ne
    0.46
     Sierra
    0.42
     Amazon
    0.42
     New
    0.42
     বিস্ফোর
    0.41
     Alter
    0.41
    Ne
    0.41
     Google
    0.40
    (".
    0.40
     Initiate
    0.40
    Activations Density 0.000%

    No Known Activations