© 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. 161167
    Prev
    Next
    INDEX
    Explanations

    professions and specific fields

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

    implementation, industry, development, flexibility

    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
     authorship
    0.43
     outbound
    0.43
     geographical
    0.43
     responding
    0.42
     admiring
    0.42
     commemorating
    0.42
     alternates
    0.41
    瀏
    0.40
     inbound
    0.39
     reflecting
    0.39
    POSITIVE LOGITS
     próp
    0.49
    льзу
    0.48
    โรค
    0.47
    Ass
    0.47
    insieme
    0.47
    ⚠
    0.46
    以来
    0.46
    뜩
    0.45
    женер
    0.45
     હાઉસ
    0.45
    Activations Density 0.001%

    No Known Activations