© 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. 40-GEMMASCOPE-2-RES-262K
    4. 166462
    Prev
    Next
    INDEX
    Explanations

    format, substitute, associate, deviate

    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
    也在
    0.43
    ilmiş
    0.39
    প্রিয়
    0.37
    Specs
    0.36
    श
    0.36
    Debt
    0.36
     Dillon
    0.35
     remembrance
    0.35
    ïque
    0.35
    మో
    0.35
    POSITIVE LOGITS
    🥯
    0.43
    AGMENT
    0.40
    🥭
    0.39
     maximale
    0.38
    🥣
    0.38
     additives
    0.38
     depolar
    0.38
     yao
    0.38
     droplets
    0.37
     penet
    0.37
    Activations Density 0.001%

    No Known Activations