© 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. 112238
    Prev
    Next
    INDEX
    Explanations

    real estate domains

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

    instructions and commands

    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
     umjet
    0.52
     songwriting
    0.48
    藝術
    0.48
     Writer
    0.48
    藝
    0.44
     romance
    0.43
     fumble
    0.43
     riguardo
    0.43
    謀
    0.43
     прад
    0.43
    POSITIVE LOGITS
    func
    0.53
    k
    0.53
    kang
    0.49
    rk
    0.49
    kannya
    0.47
    fecha
    0.46
    timestamp
    0.46
    butter
    0.46
    bees
    0.46
    sk
    0.45
    Activations Density 0.001%

    No Known Activations