© 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. 101561
    Prev
    Next
    INDEX
    Explanations

    "that is/was/are" constructions

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

    defined, given, compared, markdown, identified, fit, domain, matched

    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
    你会
    0.46
    星
    0.45
    ген
    0.45
    гі
    0.45
    Health
    0.44
    Housing
    0.42
    healthcare
    0.42
    โจ
    0.42
    専
    0.42
    暖
    0.42
    POSITIVE LOGITS
     Ainsi
    0.54
     हासिल
    0.52
     ලෙස
    0.52
     घटकर
    0.48
     પ્રમાણે
    0.48
     จับ
    0.46
     Distinct
    0.44
     Penang
    0.43
     Thats
    0.43
     महज
    0.42
    Activations Density 0.001%

    No Known Activations