© 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. 176090
    Prev
    Next
    INDEX
    Explanations

    real estate property and sales

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

    indenting, offer flexibility, any gaps

    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
    odge
    0.53
    點
    0.49
    廳
    0.48
    OWL
    0.48
    餘
    0.48
    毆
    0.48
    fficient
    0.47
    講師
    0.47
    韓
    0.47
    鴨
    0.47
    POSITIVE LOGITS
     von
    0.54
     I
    0.53
     forl
    0.50
     a
    0.50
     y
    0.49
     m
    0.48
     txt
    0.48
     curt
    0.47
     la
    0.46
     Y
    0.46
    Activations Density 0.000%

    No Known Activations