© 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. 69123
    Prev
    Next
    INDEX
    Explanations

    top local

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

    suffixes, technology, and modern concepts

    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
    PTS
    0.49
    INED
    0.49
    Karnataka
    0.48
    P
    0.47
    ISIS
    0.47
     FINANCIAL
    0.47
    isLoading
    0.46
    J
    0.46
    IN
    0.46
    Jar
    0.46
    POSITIVE LOGITS
     fragmentary
    0.49
     funcionando
    0.47
     fraction
    0.47
     secondaire
    0.47
     thiab
    0.46
     rzeczy
    0.45
    ＋
    0.45
     fonction
    0.44
     fonctionne
    0.44
     nocturnal
    0.44
    Activations Density 0.001%

    No Known Activations