© 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. 119176
    Prev
    Next
    INDEX
    Explanations

    step size and ranges

    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
     dets
    0.36
    诠
    0.36
    Voy
    0.36
    ਝ
    0.35
    zio
    0.34
    কর্মী
    0.34
    慣
    0.34
    倒
    0.34
     retreats
    0.34
     NPC
    0.33
    POSITIVE LOGITS
     Thought
    0.40
    اري
    0.39
     Flush
    0.38
     Arund
    0.37
    ніше
    0.36
     Would
    0.36
     перио
    0.36
     reconnu
    0.36
     便
    0.36
     kidneys
    0.36
    Activations Density 0.000%

    No Known Activations