© 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. 212206
    Prev
    Next
    INDEX
    Explanations

    explaining budget and plans

    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
    Arab
    0.43
     árabe
    0.42
    prong
    0.39
    orphous
    0.37
    |.|.|
    0.37
    प्त
    0.36
    breakfast
    0.36
     arabe
    0.36
     souhaite
    0.36
    ென்று
    0.36
    POSITIVE LOGITS
     straightforward
    0.42
    निर
    0.41
     separations
    0.40
     determined
    0.40
    ᒡ
    0.40
    サイクル
    0.39
     hiv
    0.39
     cycle
    0.39
     xer
    0.38
    არს
    0.38
    Activations Density 0.001%

    No Known Activations