© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 100018
    Prev
    Next
    INDEX
    Explanations

    constructor blocks

    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
     Exception
    0.59
     throws
    0.53
    throws
    0.51
     exception
    0.48
    Exception
    0.47
     println
    0.46
    抛
    0.46
    (){
    0.45
     error
    0.44
     throw
    0.44
    POSITIVE LOGITS
     ramus
    0.42
    Milwaukee
    0.42
    Dum
    0.41
    स्ट्रेल
    0.39
    ESI
    0.39
    Westinghouse
    0.38
    this
    0.37
    fond
    0.37
    Ac
    0.37
    nesi
    0.36
    Activations Density 0.005%

    No Known Activations