© 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. 104784
    Prev
    Next
    INDEX
    Explanations

    judges, write, asking what

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

    gerund ending practice

    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
    Sehr
    0.47
     گیا۔
    0.46
     ursprüng
    0.45
    ほしい
    0.44
     PARTY
    0.43
     مجموع
    0.43
     آسم
    0.43
    𝐑
    0.43
     POUR
    0.42
     بسم
    0.42
    POSITIVE LOGITS
    t
    0.58
    áce
    0.54
    பி
    0.47
     responsabil
    0.47
     Bi
    0.47
    kepsilon
    0.46
     Agric
    0.45
    ytt
    0.45
    წი
    0.45
    či
    0.45
    Activations Density 0.005%

    No Known Activations