© 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-16K
    7. 12802
    Prev
    Next
    INDEX
    Explanations

    building and facility descriptions

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

    buildings and structures

    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_16k_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
     to
    0.59
     ৩৪
    0.54
     ٣
    0.53
     bedroom
    0.51
     ৩৭
    0.51
     bedrooms
    0.51
     பகுதியில்
    0.50
     duż
    0.50
     バス
    0.50
     بازار
    0.50
    POSITIVE LOGITS
    ت
    0.71
    आर
    0.58
    होत
    0.56
    т
    0.55
    ר
    0.55
    H
    0.54
    त
    0.52
    Α
    0.49
    ัล
    0.48
    ahh
    0.48
    Activations Density 0.337%

    No Known Activations