© 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. 223209
    Prev
    Next
    INDEX
    Explanations

    running computations

    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
     niches
    0.43
     niche
    0.42
     incrementally
    0.39
     vary
    0.38
     bajas
    0.38
     fl
    0.38
     féri
    0.38
     _$
    0.38
     aumentada
    0.37
     Fl
    0.37
    POSITIVE LOGITS
    umd
    0.44
    att
    0.42
    कट
    0.40
    ষা
    0.40
     Gatt
    0.40
    Smartphone
    0.39
     História
    0.39
    atsi
    0.39
    eff
    0.39
    assem
    0.38
    Activations Density 0.000%

    No Known Activations