© 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. 1302
    Prev
    Next
    INDEX
    Explanations

    code structure and paths

    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
    ulent
    0.43
    indra
    0.42
    KX
    0.41
    uye
    0.41
    0
    0.40
    vo
    0.40
    kha
    0.40
    propion
    0.39
    邝
    0.39
    𝟬
    0.39
    POSITIVE LOGITS
     erkl
    0.43
    үз
    0.42
     mutlaka
    0.41
     razum
    0.41
     unidirectional
    0.40
    .}\
    0.38
     unbedingt
    0.37
     üt
    0.37
     filo
    0.37
     znacznie
    0.37
    Activations Density 0.000%

    No Known Activations