© 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. 12845
    Prev
    Next
    INDEX
    Explanations

    overdraft, taxi, toll

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

    transportation and communication options

    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
    e
    0.38
    ه
    0.37
     using
    0.32
     aktuell
    0.32
     Metode
    0.32
     Fahr
    0.31
     HMRC
    0.31
     Diesel
    0.30
     Produktions
    0.30
     Imran
    0.30
    POSITIVE LOGITS
     профилакти
    0.39
    Ἥ
    0.38
     ла
    0.38
    рів
    0.37
     школи
    0.37
    𝗩
    0.37
    ătă
    0.37
    яна
    0.37
     огра
    0.36
    𝒅
    0.36
    Activations Density 0.117%

    No Known Activations