© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 51616
    Prev
    Next
    INDEX
    Explanations

    often done, combination square, model took

    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_31_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
     империи
    0.50
     설계
    0.46
     смер
    0.46
    ське
    0.45
     роско
    0.43
    branche
    0.43
    ഌ
    0.43
    член
    0.43
    мено
    0.43
     mythological
    0.43
    POSITIVE LOGITS
    s
    0.58
     particles
    0.48
     before
    0.46
     oppure
    0.46
     settings
    0.45
     centrifuged
    0.45
     Depending
    0.45
    ua
    0.44
     Mungkin
    0.44
     dosing
    0.44
    Activations Density 0.002%

    No Known Activations