© 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. 42914
    Prev
    Next
    INDEX
    Explanations

    words after common prepositions

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

    Understanding specific concepts

    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
    ニ
    0.50
     pasos
    0.50
    Gor
    0.48
    dad
    0.47
     ch
    0.46
    trading
    0.45
    ेलर
    0.44
    Soon
    0.44
    とき
    0.44
    ボス
    0.44
    POSITIVE LOGITS
     Bianchi
    0.57
     Dieser
    0.54
     Gita
    0.51
    zers
    0.50
    꺾
    0.49
     Rakyat
    0.48
     Zudem
    0.48
     Кла
    0.48
     Ovaj
    0.48
     Obwohl
    0.48
    Activations Density 0.000%

    No Known Activations