© 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. 168156
    Prev
    Next
    INDEX
    Explanations

    ultimately or surprisingly

    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
     フォー
    0.38
     jobless
    0.37
     b
    0.36
    ivable
    0.36
     Print
    0.35
     Enabling
    0.35
    Omn
    0.35
    تر
    0.35
     د
    0.34
     সাক্ষ
    0.34
    POSITIVE LOGITS
    abhavena
    0.48
    abhavam
    0.43
    నికి
    0.42
    ahati
    0.41
     alimento
    0.41
     kemenangan
    0.40
    lardır
    0.40
    ভিতে
    0.40
     женщи
    0.40
     jati
    0.40
    Activations Density 0.003%

    No Known Activations