© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    source code

    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
     daño
    0.44
    போ
    0.42
    烈
    0.41
    队长
    0.40
    ጦ
    0.40
     стра
    0.39
    اري
    0.39
    stufe
    0.39
     причине
    0.39
     сцене
    0.39
    POSITIVE LOGITS
     źród
    0.71
     Source
    0.66
     sources
    0.65
     source
    0.65
     源
    0.64
     sumber
    0.63
    Source
    0.62
     kaynak
    0.61
     zdroj
    0.60
     SOURCE
    0.59
    Activations Density 0.024%

    No Known Activations