© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86813
    Prev
    Next
    INDEX
    Explanations

    sentence connectors

    np_acts-logits-general · gemini-2.5-flash-lite

    Lorenzo Models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jumps
    0.46
    動物
    0.45
     animals
    0.45
     sim
    0.44
     животных
    0.43
     gov
    0.42
     derived
    0.42
    棲
    0.41
     earned
    0.41
     examines
    0.41
    POSITIVE LOGITS
     изпол
    0.49
     وفي
    0.45
    Loren
    0.44
     Lorenzo
    0.43
     Ανακτήθηκε
    0.43
    alaa
    0.42
     கிழக்கு
    0.42
    ෝජ
    0.42
    ciju
    0.41
     Azz
    0.41
    Activations Density 0.001%

    No Known Activations