© 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. 31-GEMMASCOPE-2-RES-262K
    7. 34612
    Prev
    Next
    INDEX
    Explanations

    start patternslanguage planning

    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
    iyev
    0.48
     bicyclists
    0.45
     mitigate
    0.43
     ovaries
    0.43
     skaters
    0.42
    kowego
    0.42
    ଛ
    0.42
     prostitute
    0.41
    ूज
    0.41
    rophages
    0.41
    POSITIVE LOGITS
     Planung
    0.51
     плану
    0.49
    льне
    0.49
    ו
    0.47
    Plan
    0.47
     Toolkit
    0.46
     Coaching
    0.45
     hingegen
    0.45
    و
    0.45
     Tutorials
    0.45
    Activations Density 0.006%

    No Known Activations