© 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. 44767
    Prev
    Next
    INDEX
    Explanations

    breakdown of details

    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
     cycling
    0.51
     magazine
    0.46
     printed
    0.45
    尭
    0.43
     job
    0.42
     word
    0.42
     crime
    0.41
     cycled
    0.41
    ing
    0.41
     each
    0.41
    POSITIVE LOGITS
     sogenannten
    0.57
    ი
    0.54
    ní
    0.54
    ún
    0.51
     NOS
    0.51
     Besonders
    0.49
    olí
    0.49
    melden
    0.49
    Но
    0.48
    rägen
    0.48
    Activations Density 0.003%

    No Known Activations