© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20789
    Prev
    Next
    INDEX
    Explanations

    property descriptors

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

    apartments and housing

    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
    횽
    0.46
    悵
    0.41
     взгляд
    0.41
    颜值
    0.41
    鹬
    0.40
    akre
    0.40
    èrent
    0.39
    覷
    0.38
    ्रे
    0.38
    rène
    0.38
    POSITIVE LOGITS
     rooms
    0.52
     apartment
    0.52
     TON
    0.46
     garn
    0.46
    apartment
    0.46
     квартиры
    0.45
     apartments
    0.45
     حوالي
    0.45
    rooms
    0.45
     cellar
    0.45
    Activations Density 0.033%

    No Known Activations