© 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. 5201
    Prev
    Next
    INDEX
    Explanations

    positive descriptors for nouns

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

    positive qualities for tools and technology

    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
     (
    0.34
    :
    0.34
     America
    0.30
     monies
    0.29
     Americans
    0.28
     chaired
    0.27
     cosidd
    0.27
    人も
    0.27
     treino
    0.25
    ®.
    0.25
    POSITIVE LOGITS
    💼
    0.32
    <unused2169>
    0.30
    <0xCD>
    0.29
     Υ
    0.28
    ུ
    0.28
    ρια
    0.28
    ⁤
    0.26
     Боль
    0.25
    🔍
    0.25
    Fcm
    0.25
    Activations Density 0.022%

    No Known Activations