© 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. 89118
    Prev
    Next
    INDEX
    Explanations

    communication embedding

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

    different relationships, taxes, situations

    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
    દ્
    0.55
    ఈ
    0.52
    \,.
    0.50
    𝒊
    0.50
    екст
    0.48
    瞌
    0.48
    ों
    0.47
    માં
    0.47
     গড়
    0.47
     И
    0.45
    POSITIVE LOGITS
    2
    0.46
     Masaki
    0.46
     survived
    0.44
     foreigner
    0.44
     décor
    0.43
     communication
    0.43
    usa
    0.43
    uri
    0.43
     because
    0.43
    UP
    0.42
    Activations Density 0.000%

    No Known Activations