© 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. 161888
    Prev
    Next
    INDEX
    Explanations

    rental real estate listings

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

    following lists or descriptions

    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
    2
    0.55
     Casper
    0.49
    ink
    0.48
     Runners
    0.48
     Kong
    0.48
     Ui
    0.47
     นัก
    0.46
     linger
    0.45
     Tach
    0.45
     Racer
    0.45
    POSITIVE LOGITS
    괵
    0.56
     disposiciones
    0.50
    ک
    0.50
    ມ
    0.50
    ດ້
    0.49
    Baş
    0.49
     necessaria
    0.49
     procedimentos
    0.48
    μβ
    0.48
     striis
    0.48
    Activations Density 0.001%

    No Known Activations