© 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. 39339
    Prev
    Next
    INDEX
    Explanations

    do's and don'ts of online purchases

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

    introduction phrases

    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
     escolas
    0.51
    學校
    0.47
    辖
    0.47
     중심
    0.47
     primacy
    0.46
     လူ
    0.46
    مارسة
    0.45
     Consciousness
    0.44
     skupiny
    0.43
     Socrates
    0.43
    POSITIVE LOGITS
    ีย
    0.43
    GW
    0.43
    新
    0.43
    vet
    0.42
    iglie
    0.42
    annon
    0.42
     environmentally
    0.42
    POD
    0.41
     rejuven
    0.40
    about
    0.40
    Activations Density 0.001%

    No Known Activations