© 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. 149481
    Prev
    Next
    INDEX
    Explanations

    business topics and services

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

    security related terms

    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
    obacillus
    0.45
    上前
    0.42
    ខ្ញុំ
    0.42
     λι
    0.41
    ώ
    0.41
    ლებიც
    0.41
    려
    0.41
     슬
    0.40
    婀
    0.40
    那个
    0.40
    POSITIVE LOGITS
     hotels
    0.53
     industrie
    0.53
     lounges
    0.51
     scalable
    0.49
     Hotels
    0.49
     эффектив
    0.49
     effektiv
    0.48
     efficient
    0.48
     retailers
    0.47
     implementación
    0.47
    Activations Density 0.001%

    No Known Activations